Target for image autonomous identification, target coding method and image analysis method

Abstract

The invention relates to the field of vision measurement, in particular to a target for image autonomous identification, a target coding method and an image analysis method. The target comprises a target rod, a target seat and a target lamp, one end of the target rod is adjustably installed on the target seat, and the target lamp is installed on the target rod and can display light on the front face and the rear face of the target rod. The target lamp comprises a rear scattering cover, a rear hyperboloid reflection cavity, a reflection cone, multiple lamp beads, a front hyperboloid reflection cavity and a front scattering cover, the rear hyperboloid reflection cavity and the front hyperboloid reflection cavity are in butt joint, the reflection cone is clamped and fixed in the rear hyperboloid reflection cavity and the front hyperboloid reflection cavity, the lamp beads are arranged on the front side and the rear side of the reflection cone in a scattered mode, and the front scattering cover is arranged at the front end of the front hyperboloid reflection cavity. And the rear scattering cover is arranged at the rear end of the rear hyperboloid reflection cavity. The coding device comprises a far-end host, more than one handheld terminal and more than one target coding module. And the handheld terminal is used for communicating with the remote host to perform database synchronization, communicating with the target coding module and performing addition, deletion, checking and modification on the target coding information.

Description

Technical Field

[0001] The present invention relates to the field of visual measurement technology, and in particular to a target, a target light, an imaging device, a coding device and a method for autonomous marking. Background Art

[0002] When using photogrammetry for visual positioning, it is necessary to place external reference targets within the measurement range and match the targets on the camera image with the targets in the real space to establish the control field of the visual system. Currently, most reference targets remain relatively still with the camera. They are pre-identified and marked in the images captured by the camera. The identity tags of various targets are not included in the intrinsic attributes of the image. Their initialization marking is mainly achieved through manual confirmation, spatial position analysis and other methods. It is applicable to small-scale scenes, static cameras, and a small number of targets. However, for large-scale cluster cameras and multi-target scenes (such as Figure 1 As shown in the figure, the cameras are in dynamic cluster operation, and it is difficult to initialize the targets of each camera one by one. The number of targets recognized by each camera is large and difficult to distinguish (such as Figure 2 As shown in Figure 2, target recognition is more difficult when any camera position is dynamically switched (e.g. Figure 3 In summary, it is necessary to develop a target and autonomous identification technology that can adapt to large scenes and meet the recognition requirements of cluster dynamic cameras, and embed the target identity information into the image attributes to improve the accuracy and efficiency of visual positioning.

[0003] In order to realize the above vision, it is necessary to arrange several targets with known coordinates in space. By identifying the targets on the image and assigning the corresponding known coordinates, the external elements of the camera (referring to the three spatial coordinates and three rotational postures of the camera in space) can be determined. However, there is more than one target in the image, so the targets need to be numbered, and then the targets on each image need to be identified, and the identified targets need to be matched one by one with the numbers.

[0004] Currently, computer graphics technology can identify targets from background images, but it is difficult to match the identified targets with their numbers (i.e., the initialization of the target coordinates), which is often completed through manual initialization. This method is less efficient when the number of images spanned by the target is large. When there is an immediate computing demand, the images taken by the camera are often binary images with almost no background reference, which makes it even more difficult to match the target number.

[0005] On the basis of realizing that the target identity tag is included in the intrinsic attributes of the image, the camera needs to capture light sources of different wavelengths emitted from the same spatial position at the same time at the moment of shooting, and generate several images without parallax, and obtain the target number information by superimposing the images. This requires the camera to be able to obtain images of the same target at the same time, different wavelengths, equal intensity, and no parallax. Images of different wavelengths can be solved by optical filters, which are relatively mature at present; but for the acquisition of images of the same object, at the same time, with equal intensity and no parallax, the main methods currently used are as follows: Method 1: Use a multi-lens multi-filter camera This method can simultaneously capture light sources of different wavelengths emitted by the same target. However, since multiple cameras are simultaneously capturing images, the spatial positions of each camera cannot be completely consistent (e.g. Figure 4 As shown in the figure, the parallax of the captured image cannot be eliminated (as shown in the figure). Figure 5 As shown in the figure), after the multi-band images are superimposed, the images of the target cannot overlap, making it difficult to achieve self-identification of the target.

[0006] Method 2: Single-lens multi-filter camera This method can capture light sources of different wavelengths (such as Figure 6 As shown in the figure). Since it takes time to switch the filter, the camera can only form an image after the filter is switched. Therefore, during the process of switching the filter several times, the target or the camera may have been slightly disturbed. Therefore, the various wavelength images captured do not record the position of the target at the same time. Because the disturbance of the camera or the target will cause the image of the target to not overlap, it is also difficult to achieve self-identification of the target (such as Figure 7 as shown).

[0007] Method 3: Optical image splitting device The key to achieving the imaging function of the aforementioned target lies in the image splitting, which is currently mainly carried out by optical methods. It uses a beam splitter to decompose the same light beam and then form an image, but there are the following limitations: First, the current beam splitting by the beam splitter is only a simple image splitting, and it does not have the function of multi-band light source filtering, making it difficult to achieve synchronous imaging of co-located multi-wave light sources. Second, no device or method has been proposed to strictly control the parallax of the image, making it difficult to ensure the synchronous focusing and equal size of multiple images, resulting in parallax or defocusing between images. Third, when the position of the camera and the light source is not specific (generally a horizontal light beam in the laboratory, and multiple and divergent light sources in reality), the incident angle of each beam of light after being split by the beam splitter is different. After multiple refractions and reflections, it is impossible to ensure that the light intensity of each split image remains consistent, resulting in overexposure or underexposure of the image. Due to the above three limitations, the generated image has problems such as missing details and parallax (such as Figure 8As shown in the figure), all of these will result in the inability to overlap the images when the multi-band images are superimposed, making it difficult to achieve self-identification of the target. Summary of the invention

[0008] The present invention provides a target, a target light, an imaging device, a coding device and a method for autonomous identification, which are used to solve the technical problem that it is difficult to perform initialization identification of targets for a large number of cameras one by one in the existing visual measurement technology.

[0009] To achieve the above-mentioned purpose, the present invention provides a target for autonomous image identification, including a target rod, a target base and a target light. One end of the target rod can be adjustably mounted on the target base, and the target light is installed on the target rod and can display light on the front and back surfaces of the target rod.

[0010] As a further improvement of the above technical solution: The target base is provided with a base frame, and a group of mounting and fixing components are respectively provided at both ends of the base frame. The mounting and fixing components include fixing fasteners and a pair of leveling bolts. The target base is provided with a mounting through hole for installing the fixing fasteners, and leveling screw holes are respectively provided on both sides of the mounting through hole for installing a pair of leveling bolts.

[0011] The bottom of the leveling bolt is spherical.

[0012] The base frame is provided with an arc guide groove, the target rod is hinged to the target seat, and the hinge point is located at the center of the arc guide groove. A locking screw is slidably provided on the arc guide groove, and the locking screw cooperates with the target rod to fix the target rod at a specified position.

[0013] There are three target lamps, which are evenly spaced along the target pole, and the lights displayed by the three target lamps on the front and rear surfaces are the same in the same direction and different in different directions.

[0014] The surface of the target rod is provided with a low-reflectivity matte coating.

[0015] A target light for a target used for autonomous image identification as described above, comprising a rear scattering cover, a rear hyperbolic reflection cavity, a reflection cone, lamp beads, a front hyperbolic reflection cavity and a front scattering cover, wherein the rear hyperbolic reflection cavity is docked with the front hyperbolic reflection cavity and the reflection cone is clamped and fixed inside, a plurality of lamp beads are provided and dispersedly arranged on the front and rear sides of the reflection cone, the front scattering cover is installed at the front end of the front hyperbolic reflection cavity, and the rear scattering cover is installed at the rear end of the rear hyperbolic reflection cavity.

[0016] As a further improvement of the above technical solution: A light-shielding hole is arranged in the center of the front scattering cover or the rear scattering cover, and a light-shielding tube is arranged at one end of the reflection cone, and the light-shielding tube is sleeved in the light-shielding hole.

[0017] The lamp beads include LED lamp beads with multiple different wavelengths. LED lamp beads with multiple different wavelengths are arranged on both the front and rear sides of the reflective cone. The LED lamp beads with multiple different wavelengths on the same side of the reflective cone are arranged in a staggered manner.

[0018] The lamp beads on the front and rear sides of the reflective cone are arranged alternately.

[0019] The optical centers of the lamp beads on the front and rear sides of the reflection cone are located on the same plane.

[0020] The rear hyperbolic reflection cavity, the front hyperbolic reflection cavity and the reflection cone are coaxially arranged.

[0021] A method for fixing the target for image autonomous marking as described above on an uneven surface comprises the following steps: S1: Pre-installation: Pass the fixing fastener through the installation through hole on the target base and drive it into the uneven surface, and make the fixing fastener not completely press the target base.

[0022] S2: Leveling: screw the leveling bolts into the leveling screw holes so that the spherical part at the bottom of each leveling bolt contacts and abuts against the uneven surface. Adjust the screwing depth of each leveling bolt so that the posture of the target seat tends to the target installation posture.

[0023] S3: Fixing. When the target base reaches the target installation posture, tighten the fixing fasteners to completely fix the target base, thus completing the fixed installation of the target on the uneven surface.

[0024] A device for iso-intensity parallax-free synchronous image splitting and multi-band imaging comprises a lens and a frame, wherein the lens is mounted on the frame, and a light splitting channel and a plurality of imaging components are arranged in the frame, wherein the light splitting channel transmits iso-intensity light beams formed by multi-level light splitting and reflection of light incident from the lens to each imaging component, and the imaging component comprises a focusing lens, an imaging sensor and a band filter for allowing a light beam of a specific wavelength to pass through.

[0025] As a further improvement of the above technical solution: The imaging components are provided with four groups, and the splitting channel is provided with a primary beam splitter and two secondary beam splitters. After the incident light is dispersed into two beams by the primary beam splitter, the two beams are dispersed into two beams again by a secondary beam splitter respectively, forming a total of four beams of light that are transmitted to the four groups of imaging components respectively.

[0026] The incident light is dispersed into a first beam of light and a second beam of light by a first-level beam splitter, the first beam of light is reflected by a first reflector and then directed to a second-level beam splitter, dispersed into two beams of light by the second-level beam splitter, and then respectively reflected into a corresponding imaging component by a second reflector and a third reflector; the second beam of light is directly directed to another second-level beam splitter, dispersed into two beams of light by the second-level beam splitter, one of which is reflected into a corresponding imaging component by a fourth reflector and a fifth reflector in sequence, and the other is reflected into a corresponding imaging component by a sixth reflector and a seventh reflector in sequence.

[0027] A secondary beam splitter and a residual light absorbing cavity are arranged between the secondary beam splitter and the imaging component.

[0028] The primary beam splitter, the secondary beam splitter and the secondary beam splitter are arranged in parallel.

[0029] The first reflector, the fourth reflector and the sixth reflector are arranged in parallel; the second reflector, the third reflector, the fifth reflector and the seventh reflector are arranged in parallel.

[0030] A heat insulation cavity is arranged inside the outer shell surface of the frame.

[0031] A heat insulation cavity is arranged in the middle of the frame.

[0032] A coding device for target coding comprises a remote host, one or more handheld terminals and one or more target coding modules.

[0033] The handheld terminal is used to communicate with the remote host to synchronize the database, and is also used to communicate with the target coding module to add, delete, check and modify the target coding information.

[0034] The target encoding module is integrated in the target, and is used to synchronize the real-time encoding information of the target to the remote host; it is also used to communicate with the handheld terminal to receive addition, deletion, query and modification instructions from the handheld terminal; it is also used to send the target's encoding and status information to the handheld terminal.

[0035] As a further improvement of the above technical solution: The handheld terminal includes a first radio frequency unit, a first storage unit, a first calculation unit and a WIFI unit.

[0036] The first radio frequency unit includes an RFID tag for communicating with the target encoding module.

[0037] The first storage unit is used to store data of the handheld terminal.

[0038] The first calculation unit is used for calculating the coding information of the handheld terminal.

[0039] The WIFI unit is used to communicate with the remote host.

[0040] The target encoding module includes a second radio frequency unit, a second storage unit, a second calculation unit and a NET unit.

[0041] The second radio frequency unit includes an RFID tag, and is used for communicating with the handheld terminal.

[0042] The second storage unit is used to store data of the target encoding module.

[0043] The second calculation unit is used for calculating the coding information of the target coding module.

[0044] The NET unit is used for communicating with the remote host.

[0045] The handheld terminal communicates with the target encoding module via a first radio frequency unit and a second radio frequency unit.

[0046] The network relationship between the remote host and the one or more target encoding modules includes: The remote host can perform unidirectional reading and writing of data to the one or more target encoding modules.

[0047] The network relationship between the remote host and the one or more handheld terminals includes: The remote host can read and write data to the one or more handheld terminals.

[0048] The one or more handheld terminals are capable of reading data from the remote host.

[0049] The remote host can publish information to the outside through a mobile network, and the mobile network includes a network provided by a communication service provider.

[0050] The network relationship between the handheld terminal and the target encoding module includes: The handheld terminal can read data from the target encoding module.

[0051] Before the handheld terminal reads data from the target encoding module, the handheld terminal needs to communicate with the remote host to synchronize the database.

[0052] A target coding control method, based on the above-mentioned coding device for target coding, comprises: T1. The handheld terminal communicates with the remote host to synchronize the database, communicates with the target coding module and adds, deletes, checks and modifies the target coding information.

[0053] T2. Communicate with the handheld terminal through the target coding module to receive addition, deletion, query and modification instructions from the handheld terminal; send the target coding and status information to the handheld terminal through the target coding module.

[0054] As a further improvement of the above technical solution: The T1 includes: A1: For the target to be initialized or modified in coding, a handheld terminal is used to synchronize the coding library with a remote host through a WIFI unit and update the coding library in the first storage unit.

[0055] A2: Input the proposed target number through the handheld terminal and encode it through the first calculation unit.

[0056] A3: The first calculation unit reads the data in the first storage unit and compares the input, encoded target number with it. If it is repeated with the existing code, it returns to re-enter; if it is not repeated, the input, encoded target number is written into the first storage unit.

[0057] A4: Trigger the RFID tag of the first radio frequency unit to transmit to the RFID tag of the target second radio frequency unit.

[0058] A5: When the RFID tag of the second radio frequency unit receives the code writing instruction, it triggers the second calculation unit to read and write instructions, and the second storage unit receives and writes the new code.

[0059] A6: The new code written into the second storage unit is synchronized to the remote host through the NET unit, and its code library is updated.

[0060] A7: The second calculation unit outputs the new code of the second storage unit to the corresponding lamp beads of each target light to control the on and off combination of the lamp beads.

[0061] The T2 includes: B1: When the handheld terminal reaches the sensing range of the RFID tag of the second radio frequency unit of the target, the RFID tag of the first radio frequency unit on the handheld terminal communicates and activates with the RFID tag of the second radio frequency unit on the target.

[0062] B2: When the RFID tag of the second radio frequency unit on the target receives a query instruction, the read and write function of the second calculation unit is triggered to read the latest target coding information and working status information in the second storage unit.

[0063] B3: The RFID tag of the second radio frequency unit on the target feeds back the latest target coding information and working status information to the RFID tag of the first radio frequency unit on the handheld terminal, which is then decoded by the first calculation unit and displayed on the handheld terminal.

[0064] The method also includes: reading, writing, collecting and verifying the target's coded information through the remote host, and adjusting the on and off combination of the target light.

[0065] The reading, writing, collecting and modifying of the target's coded information by the remote host includes: C1: The remote host sends coded information collection instructions to each target.

[0066] C2: Trigger the second computing unit of each target to execute the coding information read and write instructions, and send the coding information stored in the second storage unit to the remote host through the NET unit.

[0067] C3: The remote host verifies the collected target coding information. If there is a duplicate code, the duplicate code is changed, a code change instruction is issued to the corresponding target, and the changed coding information is sent to the corresponding target.

[0068] C4: The second computing unit of the corresponding target receives the code modification instruction sent by the remote host and the modified coding information, and writes the modified coding information into the second storage unit for refreshing.

[0069] C5: The second calculation unit controls the corresponding lamp beads of the target light according to the modified coding information and adjusts the lighting combination thereof.

[0070] Also includes: Status monitoring: When the target light fails, the target is monitored through the encoding device.

[0071] Power failure recovery: When the system is powered off and then restored, the target light returns to the default state, and the encoding device is used to restart the target light to restore the preset state of the target.

[0072] The condition monitoring includes: D1: Optical simulation is used to calculate the most unfavorable light distribution for different numbers of damaged lamp beads, and the allowable number of damaged lamp beads is determined by comprehensively considering the light uniformity and the minimum light resolution of the camera.

[0073] D2. The on and off status of each lamp bead is collected at a preset frequency through the second calculation unit, and a corresponding monitoring code is generated; for lamp beads of a certain wavelength in the same target lamp, when the number of damaged lamp beads collected is the number allowed in D1, the lamp bead is still recorded as all lit, otherwise it is recorded as all off; when the lamp bead is marked as all off, the corresponding monitoring code is written into the second storage unit.

[0074] D3. Compare the monitoring code generated in D2 with the original code in the second storage unit. If the comparison results are consistent, it is determined that the wavelength lamp bead is normal and the current state is maintained; if the comparison results are inconsistent, it is determined that the wavelength lamp bead is damaged, and the second calculation unit sends a lighting termination instruction, and all target lights of the target are turned off.

[0075] D4: For the situation determined as damage in D3, the second storage unit sends the stored monitoring code to the remote host through the NET unit and issues an alarm for maintenance.

[0076] D5: The remote host publishes maintenance information to the off-site terminal via the mobile network.

[0077] The power failure recovery includes: E1: The target coding information is stored in the second storage unit before power failure.

[0078] E2: The power-on information is monitored through the second computing unit, and the target light self-check is performed according to D1 to D5.

[0079] E3: For a target light that has self-tested normally, the second calculation unit outputs the target code of the second storage unit to the corresponding lamp beads of the target light, and restores the on and off combination of the lamp beads.

[0080] A target coding method, based on the above-mentioned target and target light, comprises: Assume that there are a target lamps on a single target, each of which has lamp beads of b wavelengths. Excluding the target whose lamp is completely extinguished, each target lamp has a total of 2 b -1 combination; and each target has a target lamp, so for a target with a target lamp, each with b wavelengths, the number of target numbers that can be expressed is: (2 b -1) a , the encoding method is: F1: Number of coding bits for a single target: Each target light has b wavelengths of lamp beads. Each wavelength of lamp beads needs to occupy 1 bit of coding to represent the two states of on or off, where 1 represents on and 0 represents off. Therefore, each target light requires b bits of coding, and a target light of a single target requires a·b bits of coding.

[0081] F2: Single target light coding: For any target light i on the target, the on and off status codes of b wavelengths are sequentially connected into a target light coding to represent the identity of the current target light. Each target light coding has b bits.

[0082] F3: Single target code: Connect the single target light codes from the 1st target light to the bth target light in sequence from left to right to obtain the code of the entire target.

[0083] F4: Convert target number and target code.

[0084] As a further improvement of the above technical solution: The F4 includes: Convert target number to target code: G1: Assume that the user inputs the decimal number of the target to be encoded through the handheld terminal or remote host as k 10 , compare with the existing code according to steps A1 to A7. If it is the same as the existing code, return to prompt for re-entry, otherwise enter G2.

[0085] G2: Assume that each target has a target lights, each target light has b wavelengths, and the decimal number K is calculated by the first calculation unit or the remote host. 10 Convert to 2 b Base code K 2b , where number K 10 The initial value of is: .

[0086] G3: Check K through the first computing unit or remote host 2b Does it contain 0? If it does, then K 10 After adding 1, return to G2 and recalculate; if it does not contain 0, enter G4.

[0087] G4: Calculate K 10 -K0+1, and the decimal number k entered by the user 10 Compare, if K 10 -K0+1=k 10 , then K 10 Convert to binary code K2 and write into the second storage unit according to the method from A1 to A7; if K 10 -K0+1≠k 10 , then K 10 After adding 1, return to G2 and recalculate.

[0088] The F4 also includes: Convert target codes to target numbers: H1: According to B1 to B3, the handheld terminal or the remote host reads the binary code K2 in the second storage unit.

[0089] H2: Convert the binary code K2 to 2 through the first computing unit or the remote host b Base code K 2-2b .

[0090] H3: The first computing unit or the remote host converts the decimal code K 10 Convert to 2 b Base code K 2b , where K 10 The calculation of initial value K0 is the same as G2.

[0091] H4: K is controlled by the first computing unit or the remote host 2-2b With K 2b For comparison, if K 2b =K 2-2b , then K 10 -K0+1 output is the decimal number of binary code K2; if K 2b ≠K 2-2b , then K 10 After adding 1, return to H3 and recalculate.

[0092] A method for decoding a target light image, based on the above-mentioned equal light intensity parallax-free synchronous image splitting and multi-band imaging device, obtains a target light image set of a target cluster composed of the above-mentioned target and the above-mentioned target light, and decodes the target light image set, comprising the following steps: R1. Identify the target light spots and target light directions on the images of each wavelength in the target light image set, and remove the target light spots that do not meet the preset requirements.

[0093] R2. Screen the light spots of each wavelength image, merge the light spots from the same target light in each wavelength image to obtain the target light image, and solve the coordinates and area of ​​the bull's eye of the target light image.

[0094] R3. Classify the target lights according to the area of ​​their images, and group the target lights with similar areas as the same target.

[0095] The R1 comprises: I1: Binarize the forward and backward target light images respectively, obtain the outer boundary through Canny edge detection, and get the spot area; restore the center coordinates of the target light.

[0096] I2: Calculate the variability E of the light spot in the image R , according to the E R Determine the viewing direction.

[0097] I3: For each image, select a light spot with the smallest variation to determine the viewing direction.

[0098] The I1 includes: The forward and backward target light images are binarized respectively.

[0099] The identified boundary pixel center is stored as the boundary point (x Bi , j , y Bi , j ), (x Bi , j , y Bi , j ) represents the coordinates of the jth boundary point of the ith light spot; the total pixel area A inside the boundary is calculated i .

[0100] The coordinates of the center point G (x Gi , j , y Gi , j ), (x Gi , j ,y Gi , j ) represents the center of the ith spot. The central dark area is not considered when calculating the backward target light. Gi , j , y Gi , j ): .

[0101] The I2 includes: I21: Calculate the centroid G of the i-th light spot i The distance S to the jth boundary point i , j : .

[0102] I22: Calculate the equivalent circle radius R of the i-th spot ei : .

[0103] I23: For the i-th light spot, the equivalent circle radius R ei As a reference, calculate S i , j With the equivalent circle radius R ei The deviation, E Ri That is the variability of the light spot: .

[0104] E Ri The smaller the value, the lower the degree of contour change caused by occlusion. When the light spot is a standard circle, the value should be 0.

[0105] The I3 includes: I31: Taking the center of the target light spot as the starting point and the outer boundary of the detection as the limit, obtain the distribution of the gray value k of the image along the x and y directions respectively, and calculate the corresponding gray sample variance S respectively x and S y : .

[0106] .

[0107] I32: Construct the targeted discriminant: .

[0108] I33: If Δ=0, the target light in the image is determined to be facing forward; if Δ≠0, the target light in the image is determined to be facing backward.

[0109] The R1 further comprises: According to the variation E R Combined spot area A i The integrity of the light spot is evaluated, and the light spots that meet the following conditions should be eliminated: in is the variation threshold of the unobstructed light spot.

[0110] The decoding method further comprises: Calibrate the variability threshold and determine the initial value of the variability threshold: Q1: Use the light targets arranged on site as calibration objects and set all light targets to λ through the remote host. k Wavelength, k≤b, where b is the total number of wavelengths that each target light can emit, and all are lit.

[0111] Q2: Shooting λ k 1 image at wavelength, obtain the area A of each light spot in the image k,i , spot variability E Rk,i ; i≤n, n is the total number of light spots in the image.

[0112] Q3: Keep E Rk,i With A k,i The corresponding relationship between A k,i Arrange into a sequence k , n}, and obtain the corresponding spot variation sequence {E Rk,n}.

[0113] Q4: Find the sequence {E Rk,n}The minimum value of E Rk,m , sequence {A k , n The corresponding item is A k , m .

[0114] Q5: Find the sequence {E Rk,n}The maximum value of E Rk,p , sequence {A k , n The corresponding item is A k , p .

[0115] Q6: If A in Q5 k , p In the sequence {A k , n} is the smallest, then calculate λ as follows k The area under the wavelength is A k,iThe spot variation threshold E R0(k，i) : .

[0116] Q7: If A in Q5 k , p In the sequence {A k , n} is not the smallest, remove the item and re-execute Q5.

[0117] The R2 comprises: J1: Obtain the outer boundary and center coordinates of the target light image of each wavelength, and count the number of light spots in the image of each wavelength respectively. The central dark area of ​​the backward target light is not considered during the analysis.

[0118] J2: For target lights with b wavelengths, the wavelength image with the largest number of light spots is used as the reference, and its wavelength is λ t , calculate the distance between the center of each spot image of this wavelength and the center of the spot of other wavelength images: .

[0119] Among them, x k The horizontal coordinate of the center of the kth spot in the wavelength image with the largest number of spots; y k Indicates the ordinate of the center of the kth spot in the wavelength image with the largest number of spots; x λc,n Indicates wavelength as λ c The horizontal coordinate of the center of the nth spot in the wavelength image; y λc,n Indicates wavelength as λ c The vertical coordinate of the center of the nth spot in the wavelength image; D(k, λ c , n) represents the kth spot in the wavelength image with the largest number of spots and the wavelength λ c The center distance of the nth light spot in the wavelength image.

[0120] J3: At wavelength λ c Among the many points, when a certain point can make the above-calculated D(k, λ c , n) value is the smallest, then the point has the largest number of spots and the wavelength is λ t The k-th point distance is used to achieve overlap; using D(k, λ c , n), the wavelength is established as λ according to the following formula t The correspondence between each target point and other wavelength targets: .

[0121] Among them, P(λ t , k) indicates the largest number of light spots and a wavelength of λ t The kth point ofc , q) represents the wavelength λ c The qth point of P(λ t , k) overlap.

[0122] J4: Merge the light spot centers that are determined to be the same target light.

[0123] The J4 includes: J41. Equivalently merge the spot centers of different wavelengths of the same target light.

[0124] J42. Merge the spot areas of different wavelengths of the same target light.

[0125] The J41 includes: J411: Set the resolution accuracy: When calculating according to J412~J418, as the search center gradually approaches the search center point M, the step size will tend to 0; considering the discreteness of digital imaging, Δ≤δ is used as the cutoff condition, where Δ is the step size and δ is the pixel size of the imaging sensor.

[0126] J412: Determine the initial search area: Based on the center point P of the light spot with different wavelengths of the same target light λ1 ~P λm (1≤m≤b) coordinates determine the initial search range, and take min(x i )≤x≤max(x i ), min(y i )≤y≤max(y i )(1≤i≤m)area as the initial area.

[0127] J413: Determine the initial search center: J412 determines the geometric center G formed by all points in the area as the initial search center point M, the coordinates are: .

[0128] J414: Determine the initial search step length: half of the minimum value of the height and width direction of the area determined by J412 is used as the initial search step length Δ: .

[0129] J415: Search area: With the optimal point M as the center and Δ as the step length, search points are arranged in 8 orthogonal directions around it. For the first calculation, point M is point G; the coordinates of each search point are expressed as: .

[0130] J416: Target calculation: According to each search point arranged in J415, calculate the distance between it and the center points of m light spots of the same target light with different wavelengths and sum them: .

[0131] J417: Determine the accuracy according to J411. If it meets the requirements, output point M, which is the optimal point. Otherwise, adjust the search center and step size according to J418.

[0132] J418: For point M that does not meet the conditions of J417, consider the following two situations: Case 1: If M coincides with the center point M in J415, it indicates that the initial search area is too large. In this case, the step size Δ in J415 is updated to Δ / 2 to further narrow the range; then recalculate according to steps J416 to J417.

[0133] Case 2: If M does not coincide with the center point M in J415, the position of point M should be updated. In this case, point M in step J415 is updated to this point, and then steps J416 to J417 are executed.

[0134] J419: Follow steps J411 to J418 to point P λ1 ~P λm Processing is performed to merge the centers of light spots of different wavelengths of the same target light.

[0135] The J42 includes: J421: For the light spots of the same target light with different wavelengths, calculate their merged center M(x M , y M ), and then calculate the square of the distance S between the merged center M and the center of each wavelength spot i : .

[0136] J422: Based on the minimum distance deviation D calculated in J416, calculate the distance deviation weight β between the spot center of the same target light with different wavelengths and the merge center M: .

[0137] J423: According to the spot area A of the same target light with different wavelengths i , considering the image of J422 with medium-range deviation weight, calculate the weighted mean of the superposition of the spot areas of each wavelength: .

[0138] J424: Press J421~J423 to point P λ1 ~P λm The corresponding spot areas are processed to complete the merging of the spot areas of different wavelengths of the same target light.

[0139] The R3 comprises: R31: Assume that there are q homologous target lights after merging data, and the merging center of each homologous target image is (x Mi , y Mi ), the merged area is A Ci (i≤q), the central dark area of ​​the rearward target light is not considered in the analysis.

[0140] R32: A Ci Rearrange in ascending order.

[0141] R33: From A C1 To start, press A Ci With A Ci+1 Compare and calculate the relative deviation value δ i : .

[0142] R34: If δ i >δ0, then A Ci+1 With A Ci They are classified into the same target category and recorded as category r.

[0143] Otherwise, A Ci+1 The target markers classified into the next category are classified as category r+1.

[0144] Where δ0 is the area resolution.

[0145] R35: According to R31 to R34 above, if there are t types of targets in total, then discard the last type of grouped targets, that is, discard the tth group, and retain the first t-1 groups as the result of target clustering grouping.

[0146] The decoding method further comprises: Calibrate the area resolution and determine the initial value of the area resolution: P1: Use the light targets arranged on site as calibration objects, and set all light targets to λ through the remote host. k Wavelength, k≤b, where b is the total number of wavelengths that each target light can emit, and all are lit.

[0147] P2: Shooting λ k An image at a wavelength, obtain the area A of each light spot in the image k,i , i≤n, n is the total number of light spots in the image.

[0148] P3: A k,i Sort in descending order to get the sequence {A k , n}, n is the total number of spots in the image, and the difference between adjacent items Δ is calculated k,j =A k , j+1 -A k , j; j≤n, n is the total number of light spots in the image.

[0149] P4: Take δ k , 0= min(Δ k,j ) and δ k ,0>0 is taken as the area resolution of the image at this wavelength.

[0150] P5: Calculate the δ of each spot image under the type b wavelength according to P1~P4 k ,0 value.

[0151] P6: Calculate the variation value of each spot image under the wavelength of type b respectively, and select the spot with the smallest variation value as the calculation object.

[0152] P7: Take the light spot with the smallest wavelength variation value in each category as the calculation object, and calculate the deviation weight β corresponding to each wavelength of the light spot respectively. k .

[0153] P8: The δ calculated in P5 k ,0 value is calculated according to β in P7 k Perform weighted averaging to obtain the area resolution δ0: .

[0154] The decoding method further comprises: The decoding results of the target light image set are integrated into image tags to obtain first data.

[0155] The step of integrating the decoding results of the target light image set into image tags comprises: V1: Record the timestamp and camera number when the image was taken.

[0156] V2: Determine the viewing direction of the image and the available target images for screening, using code 1 for forward direction and 0 for backward direction.

[0157] V3: Different target lights can be distinguished based on wavelength combinations.

[0158] V4: Complete the coordinates of each target light image in the image plane, and use (x i , y i )Record.

[0159] V5: Find all the target lights contained in each target and store the positions of the target lights in the same group as a set.

[0160] V6: Generate a coding sequence using the set in V5 so that each target light image has a unique identifiable number.

[0161] The V6 includes: V61: If V2 is judged as 1, for each set in V5, the x-coordinates of the target lights contained therein are sorted in ascending order.

[0162] If V2 is judged to be 0, for each set in V5, the x-coordinates of the target lights contained therein are sorted in descending order.

[0163] V62: Replace the coordinates corresponding to the target light sequence in V61 with the corresponding target light code in V3 to obtain a new sequence, which is the entire target number.

[0164] The decoding method also includes completing the target autonomous identification, the steps are as follows: N1: When the camera is triggered to collect images, each wavelength of the target light image will generate a single-channel image file in the camera and transmit it to the remote host through intra-field communication.

[0165] N2: The remote host calculates and stores the image tag.

[0166] N3: Generate visual overlay images.

[0167] N4: The remote host stores the camera's "Unix timestamp", "camera number" and the "viewing direction", "band number", "target image code" and "target image center" obtained in N2 as a data file DATA.

[0168] N5: Integrate the images of each band, the visualized superimposed image, and the data file DATA into one TIFF file.

[0169] The N3 includes: N31: Generate a blank image with the same resolution as the images of each band and the color level of each pixel in each channel is 0.

[0170] N32: Traverse each band image according to the following rules and assign a value to each pixel level of the blank image generated by N31: For any pixel (i, j) of each band image in the image plane coordinate system, if the color scale value affected by any of them is 255, the color scale of the pixel (i, j) at the corresponding position in the blank image generated by N31 is assigned a value of 255; otherwise, it is assigned a value of 0.

[0171] A spatial multi-target image autonomous identification system, comprising: A target as described above; an imaging device as described above; an encoding device as described above.

[0172] The number of targets arranged is a first preset number, and they are staggered along a preset baseline. The target lights of the same shape on all targets have the same display direction of light; the target lights of adjacent targets on the same baseline are staggered in the shooting direction of the imaging device.

[0173] The number of the imaging devices arranged is a second preset number, and is used to collect the target light image on the target.

[0174] The encoding device is used to set the on and off combination of the target light, encode the target, and decode the target light image collected by the imaging device to complete the autonomous identification.

[0175] A spatial multi-target image autonomous identification method, based on the above-mentioned spatial multi-target image autonomous identification system, the method comprises: U1. Arrange target clusters: a first preset number of targets are arranged alternately along a preset baseline, and the target lights on all targets have the same shape and the same display direction of light; the target lights of adjacent targets on the same baseline are staggered in the shooting direction of the imaging device.

[0176] U2. Target coding: The coding device is used to set the on and off combination of the target lights on each target to encode the target.

[0177] U3. Capture and decode the target light image: Use the imaging device to capture the target light image on the target to obtain a target light image set; decode the target light image set to obtain decoded data, which includes the target light direction, target light image coordinates, and the number information of the target to which the target light belongs.

[0178] U4, autonomous identification: associate the decoded data with the target light image set to complete autonomous identification.

[0179] In the U1, there are more than two preset baselines, and the preset baselines are continuous space curves on any wall surface in the application scene.

[0180] The present invention has the following beneficial effects: The target for autonomous image identification of the present invention has a target pole for mounting a target lamp which can be adjustably mounted on a target base. When applied to a large-scale cluster multi-target scene, the angle of the target pole can be conveniently adjusted to prevent the target lamps on adjacent targets from blocking each other in the images formed in the camera; and all the target lamps can display lights on the front and back surfaces of the target pole, thereby realizing front and back two-way imaging in cooperation with a camera group in a large-scale cluster multi-target scene.

[0181] The target light of the present invention has a light-shielding hole in the center of the front scattering cover or the rear scattering cover, and a light-shielding tube is provided at one end of the reflection cone. The light-shielding tube is sleeved in the light-shielding hole. The light-shielding tube is used to block part of the reflected light and shape the light spot. The purpose is to achieve different light spots in the front and rear viewing directions of the target, so as to assist the camera in determining the viewing direction. Countersunk holes for installing lamp beads are provided on the front and rear sides of the reflection cone. Each countersunk hole is slightly inclined, and the countersunk holes on the front and rear sides of the reflection cone are horizontally staggered and equal in number. Based on this structure, the optical centers of all the lamp beads on the front and rear sides can be located on the same plane by reasonably setting the hole depth of the countersunk holes. Compared with the existing plane direct-illumination lamp bead layout, this structure realizes large-angle diffusion through only a small number of light beads, and ensures uniformity by controlling the aberration through the hyperbolic surface, thereby avoiding increasing the number of lamp beads to make up for the lack of illumination uniformity, and can effectively reduce the heating of the equipment. The target light of the present invention can realize a large number of target information markings through only a small number of wavelength channels. Each target light contains a combination of three wavelength channels. A combination of n target lights can realize 3 n With this kind of target marking, the amount of information that can be marked and the number of target lights increase exponentially, and the amount of information that can be expressed is huge.

[0182] The target fixing method of the present invention enables the entire target seat to contact the uneven surface of the mounting structure through four leveling bolts. The ball heads of the leveling bolts have good adaptability to the uneven surface, so that the contact points are stable and reliable. After the installation is completed, a stable connection relationship is formed between the entire target seat and the mounting structure. When the target seat is fixed to a planar structure, there is no need to install the leveling bolts. Therefore, this method can be applied to the surfaces of various structures and has more obvious advantages when installed on structures with uneven surfaces.

[0183] The equal-intensity parallax-free synchronous image splitting and multi-band imaging device of the present invention allows the light beam to be focused by the lens and then converged on the focal plane behind the lens. First, a primary spectroscope is used to split the light beam into two beams. The two beams of light pass through the spectroscopic channel respectively, and after multiple splitting and reflection, they finally arrive in front of multiple imaging components. At this time, the light intensity in front of each imaging component is equal and the image has no parallax; then, the insensitive light beam of the imaging sensor is filtered out by the filter of each imaging component to obtain parallax-free images of different wavelength channels; because the light beams in front of each imaging component are all incident and split by the same lens, the image can be ensured to have no parallax by accurately setting the position of the focusing lens; and the position of the imaging sensor can be accurately set to ensure that the light beam is accurately focused, thereby obtaining a clear image with no parallax. Since the reflected and transmitted light intensities of the beam splitter are related to the incident angle, it is difficult to ensure that the position and posture of the beam splitter relative to the incident light always remain fixed based on the prior art. The equal-intensity, parallax-free, synchronous image splitting and multi-band imaging device of the present invention constructs an ingenious optical path. For a light beam of any incident angle emitted from the focal plane, it can ensure that the incident angles of all beam splitters in the entire optical path are consistent, the incident angles of all reflectors are consistent, and an optical path compensation element is provided to ensure that the light intensity is equal when the light beam reaches the imaging component.

[0184] The encoding device for target encoding and the target encoding control method of the present invention can use a remote host and a handheld terminal to encode the target. The remote host can realize large-scale encoding operations, and the handheld terminal can realize fixed-point inspection and deletion and modification of encoding operations, which is easy to operate.

[0185] The target coding method of the present invention, based on the display capability of the target light, establishes a mapping that can dynamically describe the corresponding relationship between the binary target code and the decimal target number through a conversion function, thereby realizing the accurate conversion function between the binary target code and the decimal target number, facilitating the modification and writing of the code during the use phase, and bringing great convenience to the user.

[0186] The target light image decoding method of the present invention determines the viewing direction by determining whether the light spot is circular or annular on the premise of ensuring that the light spot is complete. The set process is: first define an indicator that can describe the difference between the residual image and the complete target image, select a target image with the smallest variation from the image for target type analysis, so as to complete the orientation of the viewing direction. In the decoding process, there is no need to arrange targets separately outside the field for calibration, and calibration can be achieved directly using the targets arranged on site; in addition, the variation threshold is adapted to the wavelength and the light spot area, taking into account different bands and different imaging areas. The difference influence is higher, and the judgment accuracy is higher; when the light spots from the same target lamp in each wavelength image are merged, the combination and matching problems of the target lamp images of each wavelength are solved. After the residual image of the target lamp is eliminated, the light spots from the light spots of each wavelength image are screened out to find out which light spots come from the same target lamp, so that the different wavelength images at the same position can be correctly combined together, and the bull's eye after the multi-band image combination is solved; the so-called merging is not simply to overlap these points, but to merge each point equivalently into the optimal point through the constructed algorithm. The characteristics of the optimal point after merging are: the optimal point and each The sum of the distances of the known points is the smallest, thereby ensuring the accuracy of the merged data; when merging the spot areas of the same target light with different wavelengths, it is not a simple matter of adding up the areas of each image and then calculating the average, but taking into account the weight of its position distribution deviation, and performing a weighted average on each area, so that the superposition of multiple band images is completed, and this algorithm further improves the accuracy of the merged data; when classifying the target light images on the same target, an algorithm based on the spot area aberration is used to classify the target light images with consistent areas as the same target, thereby improving the accuracy of the target light image collection on the same target; the above method associates and integrates the target light direction, target light image coordinates, and target number information without the help of a single image reference, thereby realizing the autonomous identification of the target image; through a TIFF file, the images of each band and their data information after joint processing are integrated, and this data processing method can effectively solve the problem of a large number of image acquisitions from each camera and the difficulty of storage and classification, and because it contains all the information starting from the original image, it has strong traceability, which is convenient for later verification and proofreading.

[0187] The spatial multi-target image autonomous identification system and spatial multi-target image autonomous identification method of the present invention include the above-mentioned targets, imaging devices, encoding devices and related control methods, and therefore have corresponding technical effects, which will not be repeated here.

[0188] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0189] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0190] Figure 1 It is a schematic diagram of a large-scale cluster camera and multi-target scenario.

[0191] Figure 2 It is a target image identified by a selected camera in a large-scale cluster camera and multi-target scenario.

[0192] Figure 3 It is a target image identified after selecting the dynamic displacement of the camera in a large-scale cluster camera and multi-target scenario.

[0193] Figure 4 This is a schematic diagram of the shooting status of a multi-lens and multi-filter camera.

[0194] Figure 5 This is a schematic diagram of the parallax between multi-band images obtained by a multi-lens and multi-filter camera.

[0195] Figure 6 This is a schematic diagram of the shooting status of a single-lens multi-filter camera.

[0196] Figure 7 This is a schematic diagram of the parallax between multi-band images obtained by a single-lens multi-filter camera.

[0197] Figure 8 It is a schematic diagram of the parallax between multi-band images obtained by an existing optical image splitting device.

[0198] Fig. 9 It is a schematic diagram of the three-dimensional structure from a first perspective of a target in a target embodiment of the present invention.

[0199] Fig.10 It is a schematic diagram of the stereoscopic structure of the target from a second viewing angle in the target embodiment of the present invention.

[0200] Fig.11 It is a schematic diagram of the split three-dimensional structure of the target in the target embodiment of the present invention.

[0201] Fig.12 It is a schematic diagram of the three-dimensional structure of the target rod of the target in the target embodiment of the present invention.

[0202] Fig.13 It is a schematic diagram of the three-dimensional structure of the target holder of the target in the target embodiment of the present invention split from the first perspective.

[0203] Fig.14 It is a schematic diagram of the three-dimensional structure of the target holder of the target in the target embodiment of the present invention when split from a second viewing angle.

[0204] Fig.15It is a three-dimensional structural schematic diagram of a target light in an embodiment of the target light of the present invention and a corresponding radial cross-sectional three-dimensional schematic diagram.

[0205] Fig.16 It is a schematic diagram of the disassembled three-dimensional structure of the target light in the target light embodiment of the present invention.

[0206] Fig.17 It is a schematic diagram of the three-dimensional structure of the reflection cone in the target light embodiment of the present invention.

[0207] Fig.18 It is a schematic diagram of the arrangement of lamp beads on the reflective cone in the target lamp embodiment of the present invention.

[0208] Fig.19 It is a comparison diagram of the lighting effects of the lamp beads in the target lamp embodiment of the present invention and the traditional lamp beads.

[0209] Fig. 20 It is a schematic diagram of the process of an embodiment of the target fixation method of the present invention.

[0210] Fig.21 It is a schematic diagram of the structure in which the target of the present invention is fixed to the installation structure.

[0211] Fig. 22 It is a cross-sectional three-dimensional structural schematic diagram of an imaging device embodiment of the present invention.

[0212] Fig.23 It is a schematic cross-sectional structure diagram of an imaging device embodiment of the present invention.

[0213] Fig.24 It is a schematic diagram of application scenario simulation of an imaging device embodiment of the present invention.

[0214] Fig.25 It is a schematic diagram of a multi-band split image captured by an imaging device embodiment of the present invention.

[0215] Fig.26 It is a control system diagram of an encoding device embodiment of the present invention.

[0216] Fig. 27 It is a schematic diagram of the network topology structure of an encoding device embodiment of the present invention.

[0217] Fig.28 This is a schematic diagram of light distribution when different numbers of lamp beads are damaged.

[0218] Fig.29 It is a schematic diagram of an embodiment of the encoding method of the present invention.

[0219] Fig.30 It is a schematic diagram of the process of converting numbers into codes in the coding method embodiment of the present invention.

[0220] Fig.31It is a schematic diagram of the process of converting codes into numbers in an embodiment of the coding method of the present invention.

[0221] Fig.32 It is a schematic diagram of a target light afterimage in an embodiment of a method for decoding a target light image of the present invention.

[0222] Fig.33 It is a schematic diagram of the grayscale distribution of the center of the target light in the decoding method embodiment of the target light image of the present invention.

[0223] Fig.34 It is a schematic diagram of the principle of multi-band image merging in an embodiment of the method for decoding target light images of the present invention.

[0224] Fig.35 It is a schematic diagram of traversal of the center distance of a multi-band target light image in an embodiment of the target light image decoding method of the present invention.

[0225] Fig.36 It is a schematic diagram of the center merging process of multi-band target light images in the decoding method embodiment of the target light image of the present invention.

[0226] Fig.37 It is a clustering schematic diagram of target light imaging of the same target in the embodiment of the target light image decoding method of the present invention.

[0227] Fig.38 It is a schematic diagram of image label generation in an embodiment of a method for decoding a target light image of the present invention.

[0228] Fig.39 It is a schematic diagram of the generation of a label image file in an embodiment of the method for decoding a target light image of the present invention.

[0229] The reference numerals in the accompanying drawings represent: 100, target pole; 200, target lamp; 201, backscattering cover; 202, back hyperboloid reflective cavity; 203, reflective cone; 204, lamp beads; 205, front hyperboloid reflective cavity; 206, front scattering cover; 207, light shielding tube; 300, target base; 301, arc guide groove; 302, locking screw; 303, chassis; 3031, fixing fastener; 3032, leveling bolt; 3033, mounting through hole; 3034, leveling screw hole; 400, lens; 500, rack; 501, light splitting channel; 5011, primary beam splitter; 5012, secondary beam splitter; 5013, secondary beam splitter; 5014, residual light absorption cavity; 502, imaging component; 5021, focusing lens mirror; 5022, band filter; 5023, imaging sensor; 503, thermal insulation cavity; 600, remote host; 601, handheld terminal; 6011, first radio frequency unit; 6012, first storage unit; 6013, first computing unit; 6014, WIFI unit; 602, target encoding module; 6021, second radio frequency unit; 6022, second storage unit; 6023, second computing unit; 6024, NET unit; L1, first beam of light; L2, second beam of light; M1, first reflector; M2, second reflector; M3, third reflector; M4, fourth reflector; M5, fifth reflector; M6, sixth reflector; M7, seventh reflector. DETAILED DESCRIPTION

[0230] The embodiments of the present invention are described in detail below with reference to the accompanying drawings, but the present invention can be implemented in many different ways as defined and covered by the claims.

[0231] Target Examples: like Figures 9 to 12 As shown, the target for autonomous image identification of this embodiment includes a target rod 100, a target base 300 and a target light 200. One end of the target rod 100 can be adjustably mounted on the target base 300, and the angle can be adjusted relative to the mounting surface of the target base 300. The target light 200 is installed in a hole reserved on the target rod 100, and can display light on the front and back surfaces of the target rod 100. The target rod 100 is formed in one step by a lightweight aluminum alloy, and a low-reflectivity matte coating is sprayed on the surface to prevent the light source emitted by the target light 200 from being reflected by it and captured by the camera to affect the image quality. The target for autonomous image identification of the present invention has a target pole 100 for mounting a target light 200 which can be adjustably mounted on a target base 300. When applied to a large-scale cluster multi-target scene, the angle of the target pole 100 can be conveniently adjusted to prevent the target lights 200 on adjacent targets from blocking each other in the images formed in the camera; and all the target lights 200 can display lights on the front and back surfaces of the target pole 100, thereby realizing front and back two-way imaging in cooperation with a camera group in a large-scale cluster multi-target scene.

[0232] like Fig.13 , Fig.14 As shown, in this embodiment, the target base 300 is provided with a base frame 303, which provides support for the rotation of the target rod and the connection with the structure, and is formed in one step by a lightweight aluminum alloy; a group of mounting and fixing components are respectively provided at both ends of the base frame 303, and the mounting and fixing components include a fixing fastener 3031 and a pair of leveling bolts 3032. The target base 300 is provided with a mounting through hole 3033 for installing the fixing fastener 3031, and leveling screw holes 3034 are arranged on both sides of the mounting through hole 3033 for installing a pair of leveling bolts 3032. The bottom of the leveling bolt 3032 is spherical, and the fixing fastener 3031 adopts an expansion bolt. During installation, a pair of leveling bolts 3032 are screwed into the leveling screw holes 3034, and the spherical part at the bottom of the leveling bolts 3032 abuts against the surface of the mounting structure. By adjusting the screwing depth of the pair of leveling bolts 3032 and the leveling screw holes 3034, the gap and distance between the base frame 303 and the mounting structure can be controlled. After the base frame 303 is basically in the required installation state, the target seat 300 is fixed to the surface of the mounting structure by installing the fixing fasteners 3031.

[0233] like Fig.13 , Fig.14 As shown, in this embodiment, an arc guide groove 301 is provided on the base frame 303, the target rod 100 is hinged to the target seat 300, and the hinge point is located at the center of the arc guide groove 301, and a locking screw 302 is slidably provided on the arc guide groove 301. The locking screw 302 cooperates with the target rod 100 to fix the target rod 100 at a specified position. The locking screw 302 includes a butterfly nut, and whether the target rod 100 can rotate is controlled by tightening or loosening the butterfly nut.

[0234] In this embodiment, three target lights 200 are provided, and the three target lights 200 are evenly spaced along the target pole 100. The three target lights 200 are all light sources that can provide multi-bands, and the lights displayed by the three target lights 200 on the front and back surfaces are the same in the same direction and different in different directions.

[0235] Target light embodiment: like Figures 15 to 18As shown, the target light of this embodiment includes a rear scattering cover 201, a rear hyperbolic reflection cavity 202, a reflection cone 203, a lamp bead 204, a front hyperbolic reflection cavity 205 and a front scattering cover 206. The rear hyperbolic reflection cavity 202 is connected to the front hyperbolic reflection cavity 205 and clamps the reflection cone 203 inside. A plurality of lamp beads 204 are provided and are dispersedly arranged on the front and rear sides of the reflection cone 203. The front scattering cover 206 is installed at the front end of the front hyperbolic reflection cavity 205, and the rear scattering cover 201 is installed at the rear end of the rear hyperbolic reflection cavity 202. The rear scattering cover 201 scatters the light reflected backwards uniformly, and the front scattering cover 206 scatters the light reflected forward uniformly. The rear hyperboloid reflection cavity 202 and the front hyperboloid reflection cavity 205 are both made of light aluminum alloy and processed in one go, which is convenient for heat dissipation of the light source. The rear hyperboloid reflection cavity 202 shapes the light path according to a certain rule and then reflects it to the rear of the target. The front hyperboloid reflection cavity 205 shapes the light path according to a certain rule and then reflects it to the front of the target. The reflection cone 203 shapes the lamp bead 204 The emitted light is turned toward the forward and backward directions in the reflection cavity respectively. The inner side surfaces of the rear scattering cover 201 and the front scattering cover 206 are spherical, and the outer side surfaces are flat. Both the inner and outer side surfaces are processed by frosting technology. A slot for installing the rear scattering cover 201 is provided on the hyperbolic reflection cavity 202, and the slot wall is sprayed with a low-reflectivity matte coating; the inner surfaces of the rear hyperbolic reflection cavity 202 and the front hyperbolic reflection cavity 205 are both curved surfaces formed by rotating a hyperbola around the central axis of the target lamp, and the surface is a metal-plated mirror.

[0236] In any embodiment, a light-shielding hole is opened in the center of the front scattering cover 206 or the rear scattering cover 201, and a light-shielding tube 207 is provided at one end of the reflection cone 203. The light-shielding tube 207 is sleeved in the light-shielding hole. In this embodiment, a light-shielding hole is opened on the rear scattering cover 201. The light-shielding tube 207 on the reflection cone 203 is an inverted cone structure, located at the top of the rear side of the reflection cone 203, and cooperates with the light-shielding hole on the rear scattering cover 201. The light-shielding tube 207 is used to block part of the reflected light and shape the light spot. The purpose is to achieve different light spots in the front and rear viewing directions of the target to assist the camera in determining the viewing direction.

[0237] In any embodiment, the lamp beads 204 include LED lamp beads of multiple different wavelengths, and LED lamp beads of multiple different wavelengths are arranged on the front and rear sides of the reflection cone 203. The LED lamp beads of multiple different wavelengths on the same side of the reflection cone 203 are arranged alternately. In this embodiment, the lamp beads 204 are LED lamp beads of three different wavelengths: red, green, and blue. The wavelength of the selected LED lamp beads has good penetration and meets the sensitivity difference requirements of the sensor.

[0238] In this embodiment, the lamp beads 204 on the front and rear sides of the reflection cone 203 are arranged in a staggered manner, the optical centers of the lamp beads 204 on the front and rear sides of the reflection cone 203 are located on the same plane, and the rear hyperboloid reflection cavity 202, the front hyperboloid reflection cavity 205 and the reflection cone 203 are arranged coaxially. Countersunk holes for installing the lamp beads 204 are provided on the front and rear sides of the reflection cone 203, each countersunk hole is arranged slightly inclined, and the countersunk holes on the front and rear sides of the reflection cone 203 are arranged horizontally and staggered, and the number is equal. Based on this structure, by reasonably setting the hole depth of the countersunk hole, the optical centers of all the lamp beads 204 on the front and rear sides can be located on the same plane; compared with the existing plane direct-illumination lamp bead layout, this structure achieves large-angle diffusion only through the light of a small number of light beads, and ensures uniformity by controlling the aberration of the hyperboloid, thereby avoiding increasing the number of lamp beads to make up for the lack of illumination uniformity, and can effectively reduce the heating of the equipment. A tray is provided on the outer periphery of the reflection cone 203 , and the tray is used to cooperate with the rear hyperboloid reflection cavity 202 and the front hyperboloid reflection cavity 205 to limit and fix the entire reflection cone 203 .

[0239] Based on the target lamp structure of the present invention, through the cooperation of the rear scattering cover 201 and the rear hyperbolic reflection cavity 202, and the cooperation of the front scattering cover 206 and the front hyperbolic reflection cavity 205, the point light source formed by each lamp bead 204 can be made equivalent to a single point light source, so that the light emitted by each lamp bead 204 has the same optical path to the scattering cover after being reflected by the inner surface of the reflection cavity, so that it has good spatial homology and uniformity. Fig.19 As shown, through optical simulation software simulation, its lighting effect is more uniform than that of traditional lamp beads.

[0240] Based on the three different wavelengths of LED lamp beads 204 of red, green and blue in this embodiment, by controlling the on and off combination of the different wavelength lamp beads 204, a single target light can form seven different combination output results, as shown in the following table: The combined output results of the front and rear sides of the target light have the same color but different shapes. Since the light shielding hole on the backscattering cover 201 cooperates with the light shielding tube 207 on the reflection cone 203, part of the reflected light is blocked, so that the light spot formed on the rear side of the target light is an annular light spot, while the front side of the target light is unblocked, so it is a circular light spot, so that the camera viewing direction can be quickly determined; the target light of this embodiment can realize a large amount of target information marking through only a small number of wavelength channels. Each target light contains 7 wavelength channel combinations. n target light combinations can realize 7 n With this kind of target marking, the amount of information that can be marked and the number of target lights increase exponentially, and the amount of information that can be expressed is huge.

[0241] In practical applications, after all targets are pre-encoded by the encoding device of the present invention, the on and off states of the target lights on each target are uniformly set and allocated. The specific encoding device, encoding method, etc. are described in the following embodiments.

[0242] Target fixation method embodiment: This embodiment is a method for fixing a target for image autonomous marking on an uneven surface based on the above target embodiment. The flow chart of the method is as follows: Fig. 20 As shown, the installation structure is as follows Fig.21 As shown, the specific steps include: S1: Pre-installation, the fixing fastener 3031 is passed through the installation through hole 3033 on the target base 300 and driven into the uneven surface, and the fixing fastener 3031 does not completely press the target base 300. Since the bottom surface of the target base 300 is a plane, it cannot be closely attached to the surface of the installation structure. There is an unstable contact point between the bottom surface of the target base 300 and the surface of the installation structure. At this time, the target base 300 is still easy to be displaced under external disturbances, and then enters the next step of installation.

[0243] S2: Leveling: screw the leveling bolts 3032 into the leveling screw holes 3034 so that the spherical part at the bottom of each leveling bolt 3032 contacts and abuts against the uneven surface, and adjust the screwing depth of each leveling bolt 3032 so that the posture of the target base 300 tends to the target installation posture.

[0244] S3: Fixing. When the target base 300 reaches the target installation posture, tighten the fixing fastener 3031 so that the target base 300 is completely fixed, thereby completing the fixed installation of the target on the uneven surface.

[0245] By adopting the method of this embodiment, the entire target seat 300 is in contact with the uneven surface of the mounting structure through the four leveling bolts 3032. The ball heads of the leveling bolts 3032 have good adaptability to the uneven surface, so that the contact points are stable and reliable. After the installation is completed, a stable connection relationship is formed between the entire target seat 300 and the mounting structure. When the target seat 300 is fixed to a planar structure, there is no need to install the leveling bolts 3032. Therefore, this method can be applied to the surfaces of various structures and has more obvious advantages when installed on structures with uneven surfaces.

[0246] Imaging device embodiment: like Figure 22 to Figure 23As shown, the equal-intensity parallax-free synchronous image splitting and multi-band imaging device of this embodiment includes a lens 400 and a frame 500. The frame 500 is mainly used to support and fix optical elements. The lens 400 is installed on the frame 500. The lens 400 is used to focus the light beam of the object to be photographed on the focal plane of the lens 400. A spectroscopic channel 501 and multiple imaging components 502 are provided in the frame 500. The spectroscopic channel 501 serves as a cavity for transmitting the main light path, and each surface of the spectroscopic channel is coated with a light-absorbing coating. The spectroscopic channel 501 transmits the light incident from the lens 400 to each imaging component 502 in the form of equal-intensity light through multiple levels of spectroscopic analysis and reflection. The imaging component 502 includes a focusing lens 5021, an imaging sensor 5023, and a band filter 5022 for allowing a light beam of a specific wavelength to pass through. The focusing lens 5021 is arranged in front of the filter 5022 to refocus each beam of light onto the imaging sensor 5023 for imaging. The focusing lenses 5021 are parallel to each other and perpendicular to the optical axis of the lens 400.

[0247] In this embodiment, the imaging assembly 502 is provided with four groups, and the light splitting channel 501 is provided with a primary beam splitter 5011 and two secondary beam splitters 5012. After the incident light is dispersed into two beams by the primary beam splitter 5011, the two beams are dispersed into two beams again by a secondary beam splitter 5012, forming a total of four beams of light, which are respectively transmitted to the four groups of imaging assemblies 502 and each beam splitter. In this embodiment, a convex lens with chromatic aberration correction is used as the focusing lens 5021, and the optical performance and size of each focusing lens 5021 are consistent; chromatic aberration is a kind of aberration, and after the light of different wavelengths is focused by the optical system, the respective imaging positions are not in the same plane. In this embodiment, it is necessary to focus the light of four wavelengths, and the focusing lens 5021 will cause the light beams of different wavelengths to be unable to be focused on the same plane position due to chromatic aberration, so chromatic aberration correction is required to reduce this difference; in this embodiment, there are four filters 5022, all of which are perpendicular to the optical axis of the lens 400, and the allowable wavelength ranges of each filter 5022 do not overlap. The imaging sensor 5023 is an electrical component for receiving each beam of light after refocusing and forming an image. In this embodiment, there are four imaging sensors 5023, which are only sensitive to the allowed wavelength of the corresponding filter 5022 and are used to output images of four different bands. Each imaging sensor 5023 is perpendicular to the optical axis of the lens 400 and is provided with a device for precise fine-tuning along its axial direction to correct the chromatic aberration of light of different wavelengths after focusing thereon. This device forms images of light sources of various bands separately. Therefore, in addition to correcting the chromatic aberration of the lens, this embodiment also achieves precise imaging by fine-tuning the imaging plane.

[0248] In this embodiment, the incident light is dispersed into a first beam of light L1 and a second beam of light L2 by a first-level beam splitter 5011. The first beam of light L1 is reflected by a first reflector M1 and then emitted to a second-level beam splitter 5012. After being dispersed into two beams of light by the second-level beam splitter 5012, the two beams of light are respectively reflected by a second reflector M2 and a third reflector M3 into a corresponding imaging component 502. The second beam of light L2 is directly emitted to another second-level beam splitter 5012. After being dispersed into two beams of light by the second-level beam splitter 5012, one of the beams is reflected by a fourth reflector M4 and a fifth reflector M5 into a corresponding imaging component 502, and the other beam of light is reflected by a sixth reflector M6 and a seventh reflector M7 into a corresponding imaging component 502.

[0249] In this embodiment, a secondary beam splitter 5013 and a residual light absorption cavity 5014 are provided between the secondary beam splitter 5012 and the imaging component 502. The residual light absorption cavity 5014 is a cavity for absorbing excess transmitted or reflected light generated in the optical path compensation process. The inner surface of the residual light absorption cavity 5014 is coated with a light-absorbing coating to prevent the residual light from interfering with other components when the beam splitters are close to other optical components.

[0250] In this embodiment, the primary beam splitter 5011, the secondary beam splitter 5012 and the secondary beam splitter 5013 are arranged in parallel, and all the beam splitters are used to decompose an incident light beam into a reflected light beam and a transmitted light beam. The optical performance and thickness of the beam splitters in this embodiment are completely consistent. The first reflector M1, the fourth reflector M4 and the sixth reflector M6 are arranged in parallel and parallel to the beam splitter; the second reflector M2, the third reflector M3, the fifth reflector M5 and the seventh reflector M7 are arranged in parallel and perpendicular to the beam splitter, and the optical performance of all the reflectors is completely consistent.

[0251] In this embodiment, a plurality of heat-insulating cavities 503 are provided inside and in the middle of the outer shell surface of the rack 500. The plurality of heat-insulating cavities 503 are separated by a plurality of stiffening ribs. The stiffening ribs, as subordinate components of the rack 500, can improve the rigidity of the rack 500 and ensure that the rack 500 does not deform. The heat-insulating cavities 503 can achieve a heat-insulating effect, reduce deformation of the rack 500 caused by temperature changes, prevent the position of the optical element from changing, and ensure the stability of the optical path.

[0252] The equal-intensity parallax-free synchronous image splitting and multi-band imaging device of the present invention allows the light beam to be focused by the lens 400 and then converged on the focal plane behind the lens. First, the light beam is split into two beams by a primary spectroscope 5011. The two light beams pass through the spectroscopic channel 501 respectively, and after multiple spectroscopic splitting and reflection, they finally reach the front of multiple imaging components 502. At this time, the light intensity in front of each imaging component 502 is equal and the image has no parallax; then, the insensitive light beam of the imaging sensor 5023 is filtered out by the filter 5022 of each imaging component 502, and the parallax-free images of different wavelength channels are obtained; because the light beams in front of each imaging component 502 are all incident and split through the same lens 400, the image can be ensured to have no parallax by accurately setting the position of the focusing lens 5021; and the position of the imaging sensor 5023 can be accurately set to ensure that the light beam is accurately focused, thereby obtaining a clear image with no parallax (such as Fig.24 , Fig.25 As shown). Since the reflected and transmitted light intensities of the beam splitter are related to the incident angle, it is difficult to ensure that the position and posture of the beam splitter relative to the incident light remain fixed based on the prior art. The equal light intensity non-parallax synchronous image splitting and multi-band imaging device of the present invention constructs an ingenious optical path. For a light beam with any incident angle emitted from the focal plane, it can ensure that the incident angles of all beam splitters in the entire optical path are consistent, and the incident angles of all reflectors are consistent. An optical path compensation element is provided to ensure that the light intensity is equal when the light beam reaches the imaging component 502.

[0253] Encoding device embodiment: like Fig.26 , Fig. 27 As shown, the encoding device for target encoding of the present embodiment includes a remote host 600, one or more handheld terminals 601 and one or more target encoding modules 602; the handheld terminal 601 is used to communicate with the remote host 600 to synchronize the database, and is also used to communicate with the target encoding module 602 and add, delete, query and modify the target encoding information; the target encoding module 602 is integrated in the target, and is used to synchronize the real-time encoding information of the target to the remote host 600, communicate with the handheld terminal 601 to receive the add, delete, query and modify instructions from the handheld terminal 601, and send the target's encoding and status information to the handheld terminal 601.

[0254] In this embodiment, the handheld terminal 601 includes a first radio frequency unit 6011, a first storage unit 6012, a first calculation unit 6013 and a WIFI unit 6014; the first radio frequency unit 6011 includes an RFID tag for communicating with the target coding module 602; the first storage unit 6012 is used to store data of the handheld terminal 601; the first calculation unit 6013 is used for calculating the coding information of the handheld terminal 601; and the WIFI unit 6014 is used to communicate with the remote host 600. The main function of the handheld terminal 601 is to initialize and modify the coding during the on-site installation and debugging of the target, synchronize with the database of the remote host 600 through the WIFI unit 6014, and ensure the accuracy and real-time performance of the database of the handheld terminal 601; communicate with the target coding module 602 through the first radio frequency unit 6011 to realize the addition, deletion, query and modification of the target coding information on site.

[0255] In this embodiment, the target coding module 602 is separately integrated in the target, including a second radio frequency unit 6021, a second storage unit 6022, a second calculation unit 6023 and a NET unit 6024; the second radio frequency unit 6021 includes an RFID tag for communicating with the handheld terminal 601; the second storage unit 6022 is used to store data of the target coding module 602; the second calculation unit 6023 is used for calculating the coding information of the target coding module 602; the NET unit 6024 is used to communicate with the remote host 600, and the handheld terminal 601 and the target coding module 602 communicate through the first radio frequency unit 6011 and the second radio frequency unit 6021, and the communication is realized through the local area network in the field. The real-time coding information of the target is synchronized to the remote host 600 through the NET unit 6024; the second radio frequency unit 6021 communicates with the first radio frequency unit 6011 of the handheld terminal 601, accepts the deletion and modification instructions of the handheld terminal 601 on the coding, and uploads the coding and status information of the target to it.

[0256] In this embodiment, the network relationship between the remote host 600 and one or more target encoding modules 602 includes: the remote host 600 can perform unidirectional reading and writing of data to one or more target encoding modules 602. The network relationship between the remote host 600 and one or more handheld terminals 601 includes: the remote host 600 can read and write data to one or more handheld terminals 601; each handheld terminal 601 can read data from the remote host 600. The remote host 600 can publish information to the outside through a mobile network, and the mobile network includes a network provided by a communication service provider. The network relationship between the handheld terminal 601 and the target encoding module 602 includes: the handheld terminal 601 can read data from the target encoding module 602, and before the handheld terminal 601 reads data from the target encoding module 602, the handheld terminal 601 needs to communicate with the remote host 600 to synchronize the database.

[0257] Target coding control method embodiment: The target coding control method of this embodiment is based on the above-mentioned coding device and target light embodiments, and the method includes: T1. The handheld terminal 601 communicates with the remote host 600 to synchronize the database, communicates with the target coding module 602 and adds, deletes, checks and modifies the target coding information.

[0258] T2. Communicate with the handheld terminal 601 through the target coding module 602 to receive the addition, deletion, query and modification instructions from the handheld terminal 601; send the target code and status information to the handheld terminal 601 through the target coding module 602.

[0259] In this embodiment, T1 and T2 are mainly used for on-site query, initialization, and modification of the target code, wherein T1 includes: A1: For the target to be initialized or modified in coding, the handheld terminal 601 is used to synchronize the coding library with the remote host 600 through the WIFI unit 6014 and update the coding library in the first storage unit 6012.

[0260] A2: Input the proposed target number through the handheld terminal 601 and encode it through the first calculation unit 6013.

[0261] A3: The first calculation unit 6013 reads the data in the first storage unit 6012 and compares the input, encoded target number with it. If it is repeated with the existing code, it returns to re-enter; if it is not repeated, the input, encoded target number is written into the first storage unit 6012.

[0262] A4: Trigger the RFID tag of the first radio frequency unit 6011 to transmit to the RFID tag of the target second radio frequency unit 6021.

[0263] A5: When the RFID tag of the second radio frequency unit 6021 receives a code writing instruction, it triggers the second calculation unit 6023 to read and write instructions, and the second storage unit 6022 receives and writes the new code.

[0264] A6: The new code written into the second storage unit 6022 is synchronized to the remote host 600 through the NET unit 6024, and its code library is updated.

[0265] A7: The second calculation unit 6023 outputs the new code of the second storage unit 6022 to the corresponding lamp bead 204 of each target light to control the on and off combination of the lamp bead 204.

[0266] In this embodiment, step T2 includes: B1: When the handheld terminal 601 reaches the sensing range of the RFID tag of the second RF unit 6021 of the target, the RFID tag of the first RF unit 6011 on the handheld terminal 601 communicates and activates with the RFID tag of the second RF unit 6021 on the target.

[0267] B2: When the RFID tag of the second radio frequency unit 6021 on the target receives a query instruction, the read and write functions of the second calculation unit 6023 are triggered to read the latest target coding information and working status information in the second storage unit 6022.

[0268] B3: The RFID tag of the second radio frequency unit 6021 on the target feeds back the latest target coding information and working status information to the RFID tag of the first radio frequency unit 6011 on the handheld terminal 601, which is then decoded by the first calculation unit 6013 and displayed on the handheld terminal 601.

[0269] In this embodiment, the target coding information can also be read, written, collected and modified by the remote host 600, and the target light on and off combination can be adjusted. This part of the method is mainly used for remote and large-scale collection and modification of target coding, specifically including: C1: The remote host 600 sends a coded information collection instruction to each target.

[0270] C2: Trigger the second computing unit 6023 of each target to execute the coding information read and write instructions, and send the coding information stored in the second storage unit 6022 to the remote host 600 through the NET unit 6024.

[0271] C3: The remote host 600 checks the collected target coding information. If there is a duplicate code, the duplicate code is changed, a code change instruction is issued to the corresponding target, and the changed coding information is sent to the corresponding target.

[0272] C4: The second computing unit 6023 of the corresponding target receives the code modification instruction sent by the remote host 600 and the modified coding information, and writes the modified coding information into the second storage unit 6022 for refreshing.

[0273] C5: The second calculation unit 6023 controls the corresponding lamp beads 204 of the target light according to the modified coding information, and adjusts the on and off combination thereof.

[0274] The target expresses information by the combination of the on and off of the lamp bead 204. If the lamp bead 204 fails and the on and off situation is inconsistent with the code, such as the damage of the lamp bead 204 of a certain wavelength, the wavelength combination of the image will be inconsistent with the actual code, causing the system to encode and decode the image incorrectly; and when the system is powered off, the target light needs to be re-lit after the power is restored, and it needs to be restored to the preset state. In this embodiment, two control modes are also included: state monitoring and power failure recovery. State monitoring: when the target light fails, the target is monitored through the encoding device; power failure recovery: when the system is powered off and the target light is restored to the default state, the target light is restarted through the encoding device to restore the preset state of the target.

[0275] In this embodiment, the specific steps of status monitoring include: D1: Optical simulation is used to calculate the most unfavorable illumination distribution for different numbers of damaged lamp beads 204, and the allowable number of damaged lamp beads 204 is determined by comprehensively considering illumination uniformity and the minimum illumination resolution of the camera; Fig.28 The illumination distribution of different numbers of damaged lamp beads 204 is shown when the number of single-wavelength lamp beads 204 is four. It can be seen from Figure (c) that when the number of damaged lamp beads 204 reaches two (the figure shows the most unfavorable working condition when two adjacent lamp beads are damaged, and the illumination is seriously eccentric at this time), the illumination distribution shows a significant low-illuminance distribution area. Therefore, when the number of single-wavelength lamp beads 204 is four, one lamp bead 204 is allowed to be damaged. This method takes into account engineering practice and economy, and allows a certain number of lamp beads 204 of the same wavelength in each target lamp to be damaged. The number of allowed damages is determined according to the above-mentioned optical simulation method.

[0276] D2. The on and off status of each lamp bead 204 is collected at a preset frequency through the second calculation unit 6023, and a corresponding monitoring code is generated; for the lamp bead 204 of a certain wavelength in the same target lamp, when the number of damaged lamp beads 204 collected is the number allowed in D1, the lamp bead 204 is still recorded as all lit, otherwise it is recorded as all extinguished; when the lamp bead 204 is marked as all extinguished, the corresponding monitoring code is written into the second storage unit 6022; taking D1 as an example, when four lamp beads 204 of a certain wavelength are in a lighting combination, it is detected that one is damaged. At this time, the system still considers that all four are lit, and its corresponding code is recorded as 1, and the monitoring code is not written into the second storage unit 6022; if it is detected that two lamp beads 204 are damaged, the system considers that all four lamp beads 204 are extinguished, and its corresponding code is recorded as 0, and the monitoring code is written into the second storage unit 6022.

[0277] D3, compare the monitoring code generated in D2 with the original code in the second storage unit 6022. If the comparison results are consistent, it is determined that the wavelength lamp bead 204 is normal and the current state is maintained; if the comparison results are inconsistent, it is determined that the wavelength lamp bead 204 is damaged, and the second calculation unit 6023 sends a lighting termination instruction, and all the target lights of the target are turned off.

[0278] D4: For the situation determined as damage in D3, the second storage unit 6022 sends the stored monitoring code to the remote host 600 through the NET unit 6024 and issues an alarm for maintenance.

[0279] D5: The remote host 600 publishes maintenance information to the off-site terminal via the mobile network.

[0280] In this embodiment, it should be noted that for power failure recovery, it can be known from the aforementioned control logic that when encoding the target, the handheld terminal 601 and the remote host 600 may read and write the target data at the same time (the reading and writing frequency of the remote host 600 is much greater than that of the handheld terminal 601). In order to ensure the accuracy and reliability of the code stored in the target, the RFID tag of the target in this embodiment is only used for communication with the handheld terminal 601 and temporary storage during encoding. The RFID tag of the target is not used as a permanent storage medium. The data processed by the second calculation unit 6023 of the target is saved in a separate second storage unit 6022. Therefore, when the power is cut off at the scene, after the power is restored, the preset state of the target is restored by reading the second storage unit 6022 instead of the target RFID tag.

[0281] The specific steps of power failure recovery in this embodiment include: E1: The second storage unit 6022 has stored the target coding information before power failure.

[0282] E2: The power-on information is monitored by the second computing unit 6023, and the target light self-check is performed according to D1 to D5.

[0283] E3: For a target light that has self-tested normally, the second calculation unit 6023 outputs the target code of the second storage unit 6022 to the corresponding lamp bead 204 of the target light, and restores the on and off combination of the lamp bead 204.

[0284] Target encoding method embodiment: A target coding method, based on the above-mentioned target and target lamp embodiment, assumes that there are a target lamps on a single target, each target lamp has lamp beads 204 of b wavelengths, and excluding the target whose target lamp is completely extinguished, each target lamp has a total of 2 b -1 combination; and each target has a target lamp, so for a target with a target lamp, each with b wavelengths, the number of target numbers that can be expressed is: (2 b -1) aIn this embodiment, a=3, b=3, and each target light has 2 3 -1=7 combinations, the number of target numbers that can be expressed is: (2 3 -1) 3 =343 kinds.

[0285] like Figure 29 to Figure 31 As shown, the target encoding method comprises the following steps: F1: The number of coding bits for a single target: Each target light has b wavelength lamp beads 204, and each wavelength lamp bead 204 needs to occupy 1 bit of coding to represent the two states of on or off, where 1 represents on and 0 represents off. Therefore, each target light requires b bits of coding, and a target lights of a single target require a·b bits of coding; in this embodiment, each target light is coded with 3 bits, and the 3 target lights of a single target are coded with 3·3=9 bits.

[0286] F2: Single target light coding: For any target light i on the target, the on / off status codes of b wavelengths are sequentially connected into a target light coding to represent the identity of the current target light. Each target light coding has b bits; Fig.29 The target light 2 has three wavelengths λ1, λ2, λ b The on and off states are 1, 1, 1 respectively. When connected into a single target light, the code is 111.

[0287] F3: Single target code: Connect the codes of the single target lights from the first target light to the bth target light in order from left to right to obtain the code of the entire target; in this embodiment, this order is globally unified, even if the backward coding will cause the code to be reversed, the coded image is read in this order when it is decoded, and they are connected in sequence to obtain the code of the entire target. Fig.29 In the forward target, the codes of the three target lights are 010, 111, and 100 respectively. After connecting them in sequence, the code of the target is 010111100; because the wavelength combination of the rearward target light is consistent with that of the forward target light, the position of the target light in the image will be reversed, and the displayed target code is 100111010.

[0288] F4: Convert target number and target code.

[0289] Since the target code is binary, it is suitable for computer processing, but it is not convenient for stage coding modification and writing. Therefore, we need to design a transcoding method that meets the following conditions: ⅰ The numbers entered by the user are consecutive decimal numbers; ⅱ The number input by the user corresponds to the code described in F3 one by one; it should be noted here that not all decimal numbers can correspond to the code described in F3, because when the decimal number is converted to binary code, there will be a situation where it is continuous 0, for example, 400 is converted to binary code as 100 000 000, according to the coding rules of F3, the corresponding target light at this time is that only the first target light is lit, and the remaining two are off, but this situation is not allowed. Therefore, when establishing the corresponding relationship, this situation should be excluded.

[0290] ⅲ The corresponding relationship in the above ⅱ should not be to search for the pre-built form, but to find a mapping that can dynamically describe the corresponding relationship, such as a conversion function. Because the pre-built form is an exhaustive idea, on the one hand, it has poor flexibility, requires a large amount of storage, and is not easy to maintain; on the other hand, it cannot reflect the corresponding relationship in essence and cannot solve the problem of discontinuous decimal encoding mentioned in ⅱ, which will cause the user terminal to avoid some numbers, which will bring great inconvenience to the user.

[0291] In view of the above problem, step F4 of this embodiment includes two parts: one is converting the target number into the target code, and the other is converting the target code into the target number.

[0292] In this embodiment, converting the target number into the target code includes: G1: Assume that the user inputs the decimal number of the target to be encoded through the handheld terminal 601 or the remote host 600 as k 10 , compare with the existing code according to steps A1 to A7. If it is the same as the existing code, return to prompt for re-entry, otherwise enter G2.

[0293] G2: Assume that each target has a target lights, each target light has b wavelengths, and the decimal number K is calculated by the first calculation unit 6013 or the remote host 600. 10 Convert to 2 b Base code K 2b In this embodiment, each target lamp has three wavelengths, so K 10 Convert to 2 3 = octal code K8, where number K 10 The initial values ​​are: .

[0294] G3: Check K through the first computing unit 6013 or the remote host 600 2b Does it contain 0? If it does, then K 10 After adding 1, return to G2 and recalculate; if it does not contain 0, enter G4.

[0295] G4: Calculate K 10-K0+1, and the decimal number k entered by the user 10 Compare, if K 10 -K0+1=k 10 , then K 10 is converted into binary code K2 and written into the second storage unit 6022 according to the method of steps A1 to A7; if K 10 -K0+1≠k 10 , then K 10 After adding 1, return to G2 and recalculate.

[0296] The essence of the above method is in 2 b Under binary encoding, find the kth code K that does not contain 0 2b , and k is used as a binary coding mapping, which not only meets the target light coding rules, but also ensures the continuity of the numbering.

[0297] In this embodiment, converting the target code into the target number includes: H1: According to B1 to B3, the binary code K2 in the second storage unit 6022 is read by the handheld terminal 601 or the remote host 600.

[0298] H2: The first computing unit 6013 or the remote host 600 converts the binary code K2 into 2 b Base code K 2-2b .

[0299] H3: The first computing unit 6013 or the remote host 600 converts the decimal code K 10 Convert to 2 b Base code K 2b , where K 10 The calculation of initial value K0 is the same as G2.

[0300] H4: Through the first computing unit 6013 or the remote host 600 to K 2-2b With K 2b For comparison, if K 2b =K 2-2b , then K 10 -K0+1 output is the decimal number of binary code K2; if K 2b ≠K 2-2b , then K 10 After adding 1, return to H3 and recalculate.

[0301] The essence of the above method is in 2 b In binary encoding, it is known that its code is K 2b, find out which code does not contain 0. The advantage is that the conversion between number and code can be completed by only using the system RAM, without occupying the space of the remote host 600, the handheld terminal 601, and the target second storage unit 6022.

[0302] To facilitate the understanding of the above method, the following table provides a section number and code of a target containing three target lights and three wavelengths for reference.

[0303] From the table above, we can see that converting decimal to 2 b The base is actually to simplify the judgment of multiple sub-codes in binary into the judgment of one code. The number of unencodable codes N can also be calculated as: .

[0304] The above coding method is based on the forward target light, and is input and decoded in order from left to right; for the backward target light, since its wavelength combination is consistent with that of the corresponding forward target light, the forward and backward reverse effects are not considered during input and decoding. The reverse coding process of the backward target light is completed through the image decoding stage.

[0305] Target light image decoding method embodiment: A method for decoding a target light image, based on the above-mentioned equal light intensity parallax-free synchronous image splitting and multi-band imaging device embodiment, obtains a target light image set of a target cluster composed of the above-mentioned target and target light embodiment, and decodes the target light image set, specifically comprising the following steps: R1. Identify the target light spots and target light directions on each wavelength image in the target light image set, and remove the target light spots that do not meet the preset requirements.

[0306] R2. Filter the light spots of each wavelength image, merge the light spots from the same target light in each wavelength image, obtain the target light image, and solve the coordinates and area of ​​the center of the target light image.

[0307] R3. Classify the target lights according to the area of ​​their images, and group the target lights with similar areas as the same target.

[0308] In this embodiment, when the imaging device collects the target image in the visual field, its viewing direction is not fixed. If the viewing direction is opposite, the collected target image is also opposite. If it is not distinguished, it will cause recognition errors according to the above coding rules. For this reason, the above target light is designed with inconsistent features in the front and back directions (a circular light spot in the front direction and an annular light spot in the back direction) so as to distinguish the viewing direction of the imaging device from the image.

[0309] Furthermore, in the process of executing step R1, since the target will inevitably be blocked from front and back, the imaging of the target light spot will be incomplete. At this time, the light spot does not present an ellipse, but a cut edge situation occurs, which we call an afterimage. According to the spatial position relationship of the target, the situation of the target image being blocked is mainly divided into the following three types: the first is corner blockage: it is mainly manifested in that the target image light spot is blocked by the corner of another target, and the overall structure is a concave polygon; the second is most of the blockage: it is mainly manifested in that most of the target image light spot is missing, and only the crescent-shaped light spot structure is exposed; the third is a small part of the blockage: it is mainly manifested in that a small part of the target image light spot is missing, and only the convex moon-shaped light spot structure is exposed.

[0310] Since the forward and backward light spots have different shapes, the forward one is circular and the backward one is annular, and the aforementioned occlusion will interfere with the judgment of the light spot type (circular or annular), regardless of whether it is a forward or backward light spot, since there is no background reference, the above-mentioned residual images will interfere with the subsequent analysis of the light spot, so they must be removed from the identified light spots and do not participate in the analysis. Therefore, it is necessary to determine the viewing direction by determining whether it is circular or annular on the premise of ensuring that the light spot is complete. The set process is: first define an indicator (variability) that can describe the difference between the residual image and the complete target image, and select a target image with the smallest variation from the image (although the target image is occluded, it is a minority after all. There must be an unoccluded target in any image, so the target image with the smallest variation must be complete) to perform target type analysis (circular or annular), thereby completing the orientation of the viewing direction, so the specific steps of R1 are as follows: I1: Binarize the forward and backward target light images respectively, obtain the outer boundary through Canny edge detection, and get the spot area; restore the center coordinates of the target light.

[0311] I2: Calculate the variability E of the light spot in the image R , according to E R To determine the viewing direction.

[0312] I3: For each image, select a light spot with the smallest variation to determine the viewing direction.

[0313] I1 includes: The forward and backward target light images are binarized respectively.

[0314] The identified boundary pixel center is stored as the boundary point (x Bi , j , y Bi , j ), (x Bi , j , y Bi , j ) represents the coordinates of the jth boundary point of the ith light spot; the total pixel area A inside the boundary is calculated i .

[0315] The coordinates of the center point G (x Gi , j , y Gi , j ), (x Gi , j ,y Gi , j ) represents the center of the ith spot. The central dark area is not considered when calculating the backward target light. Gi , j , y Gi , j ): .

[0316] I2 includes: I21: Calculate the centroid G of the i-th light spot i The distance S to the jth boundary point i , j : .

[0317] I22: Calculate the equivalent circle of the i-th spot (such as Fig.32 The dotted circle shows the radius R ei : .

[0318] I23: For the i-th light spot, the equivalent circle radius R ei As a reference, calculate S i , j With the equivalent circle radius R ei The deviation, E Ri That is the variability of the light spot: .

[0319] E Ri The smaller the value, the lower the degree of contour change caused by occlusion. When the light spot is a standard circle, the value should be 0.

[0320] I3 includes: I31: Taking the center of the target light spot as the starting point and the outer boundary of the detection as the limit, obtain the distribution of the gray value k of the image along the x and y directions respectively, and calculate the corresponding gray sample variance S respectively x and S y (like Fig.33 shown): .

[0321] .

[0322] I32: Construct the targeted discriminant: .

[0323] I33: If Δ=0, the target light in the image is determined to be facing forward; if Δ≠0, the target light in the image is determined to be facing backward.

[0324] The above step R1 also includes: According to the variation E R Combined spot area A i The integrity of the light spot is evaluated, and the light spots that meet the following conditions should be eliminated: .

[0325] in is the variation threshold of the unobstructed light spot.

[0326] Variability calibration mainly considers two aspects: for the same wavelength image, its variation is related to its spot size (i.e. the distance between the target light and the camera), because the resolution of the image is certain, the smaller the spot area, the stronger the edge jaggedness, and the greater the relative variability. On the other hand, the imaging area of ​​sensors with different wavelengths is different, and the variation threshold of each wavelength image needs to be corrected separately. The variation calibration process includes the following steps: Calibrate the variability threshold and determine the initial value of the variability threshold: Q1: Use the light targets arranged on site as calibration objects, and set all light targets to λ through the remote host 600. k Wavelength, k≤b, where b is the total number of wavelengths that each target light can emit, and all are lit.

[0327] Q2: Shooting λ k 1 image at wavelength, obtain the area A of each light spot in the image k,i , spot variability E Rk,i ; i≤n, n is the total number of light spots in the image (at this time, there may be afterimages in each light spot, not all of them are complete light spots).

[0328] Q3: Keep E Rk,i With A k,i The corresponding relationship between A k,i Arrange into a sequence k , n}, and obtain the corresponding spot variation sequence {E Rk,n}.

[0329] Q4: Find the sequence {E Rk,n}The minimum value of E Rk,m , sequence {A k , n The corresponding item is A k , m .

[0330] Q5: Find the sequence {E Rk,n}The maximum value of E Rk,p , sequence {Ak , n The corresponding item is A k , p .

[0331] Q6: If A in Q5 k , p In the sequence {A k , n} is the smallest, then calculate λ as follows k The area under the wavelength is A k,i The spot variation threshold E R0(k，i) : .

[0332] Q7: If A in Q5 k , p In the sequence {A k , n} is not the smallest, remove the item and re-execute Q5.

[0333] To facilitate the understanding of the above process, an example is given below: The image at a certain wavelength is calculated to obtain the area and variation of each spot as follows: From the above table, we can see that: Minimum Variation E Rk,2 =1.802, which corresponds to A k , 2=270; Maximum Variation E Rk,3 =3.520, which corresponds to A k , 3=151 <min({ A k , n})=145, remove and screen again; Maximum Variation E Rk,3 =2.102, which corresponds to A k , 4=145=min({ A k , n})=145, meets the requirements; When the spot area is known to be 255, its variation thresholdE R0 =1.838.

[0334] The advantage of this method for calculating the variability threshold is that there is no need to set up targets separately outside the field for calibration, and calibration can be achieved directly using targets arranged on site. In addition, the variability threshold is adapted to the wavelength and spot area, taking into account the influence of area differences in different bands and different imaging, and the judgment accuracy is higher.

[0335] In the above step R2, the light spots from the same target light in each wavelength image are merged, mainly to solve the problem of combination and matching of target light images of each wavelength. After the target light is processed by the above-mentioned residual image removal, the light spots from the light spots of each wavelength image are screened out to determine which light spots are from the same target light, so that different wavelength images at the same position can be correctly combined together, and the bull's eye after the multi-band image combination is solved.

[0336] Since each imaging element of the multi-wave imaging camera has the same image plane coordinate system, the multi-band images will be superimposed when each band image is projected onto the virtual imaging plane (the virtual imaging plane is only imaginary for ease of understanding, and each wavelength of light will not overlap and form a secondary image). Fig.34 As shown in the figure, taking three wavelength target lights as an example, when all three wavelength lamp beads are lit, the three images will be superimposed on the virtual imaging surface, and the remaining lamp bead combinations are similar. To achieve the above superposition process, it is necessary to first establish a mapping relationship for the spot data of each band image, such as Fig.35 As shown, the specific steps include: J1: Obtain the outer boundary and center coordinates of the target light image of each wavelength, and count the number of light spots in the image of each wavelength respectively. The central dark area of ​​the backward target light is not considered during the analysis.

[0337] J2: For target lights with b wavelengths, the wavelength image with the largest number of light spots is used as the reference, and its wavelength is λ t , calculate the distance between the center of each spot image of this wavelength and the center of the spot of other wavelength images: .

[0338] Among them, x k The horizontal coordinate of the center of the kth spot in the wavelength image with the largest number of spots; y k Indicates the ordinate of the center of the kth spot in the wavelength image with the largest number of spots; x λc,n Indicates wavelength as λ c The horizontal coordinate of the center of the nth spot in the wavelength image; y λc,n Indicates wavelength as λ c The vertical coordinate of the center of the nth spot in the wavelength image; D(k, λ c , n) represents the kth spot in the wavelength image with the largest number of spots and the wavelength λc The center distance of the nth light spot in the wavelength image.

[0339] J3: At wavelength λ c Among the many points, when a certain point can make the above-calculated D(k, λ c , n) value is the smallest, then the point has the largest number of spots and the wavelength is λ t The k-th point distance is used to achieve overlap; using D(k, λ c , n), the wavelength is established as λ according to the following formula t The corresponding relationship between each target point and other wavelength targets: .

[0340] Among them, P(λ t , k) indicates the largest number of light spots and a wavelength of λ t The kth point of c , q) represents the wavelength λ c The qth point of P(λ t , k) overlap.

[0341] J4: Merge the light spot centers that are determined to be the same target light.

[0342] The above-mentioned merging process from J1 to J3 only completes the classification of the light spot images of each wavelength. In the actual imaging process, due to factors such as the difference in the sensitivity of the sensor to different wavelengths, for the same target light, it is impossible to completely overlap the images of different wavelengths in spatial position and shape. There will always be deviations in position and shape (such as Fig.36 -(a)). However, when using the multi-band images of the target light to overlap and determine the wavelength combination and the center of the light spot of the target light, we hope that the centers of the light spots of each wavelength are overlapped. Therefore, it is necessary to merge the centers of the light spots of the same target light determined in J3. For the same target light with three wavelengths, the merging method in J3 is used. There are at most three image merging categories, namely: the first category, single wavelength, no merging is required; the second category, two wavelength image merging; the third category, three wavelength image merging. However, the so-called merging is not simply to overlap these points, but to construct an algorithm to equivalently merge the points into the optimal point. The optimal point after merging should have the following characteristics: the sum of the distances between the optimal point and each known point is the smallest. Based on this principle, the specific merging method in step J4 is as follows: J41. Equivalently merge the spot centers of different wavelengths of the same target light.

[0343] J42. Merge the spot areas of different wavelengths of the same target light.

[0344] Among them, J41 includes: J411: Set the resolution accuracy: When calculating according to J412~J418, as the search center gradually approaches the search center point M, the step size will tend to 0; considering the discreteness of digital imaging, Δ≤δ is used as the cutoff condition, where Δ is the step size and δ is the pixel size of the imaging sensor.

[0345] J412: Determine the initial search area: Based on the center point P of the light spot with different wavelengths of the same target light λ1 ~P λm (1≤m≤b) coordinates determine the initial search range, and take min(x i )≤x≤max(x i ), min(y i )≤y≤max(y i ) (1≤i≤m) area as the initial area; J413: Determine the initial search center: J412 determines the geometric center G formed by all points in the area as the initial search center point M, the coordinates are (such as Fig.36 -(a)): .

[0346] J414: Determine the initial search step length: Take half of the minimum value of the height and width direction of the area determined by J412 as the initial search step length Δ (such as Fig.36 -(b)): .

[0347] J415: Search area: With the optimal point M as the center and Δ as the step length, search points are arranged in 8 orthogonal directions around it. For the first calculation, point M is point G; the coordinates of each search point are expressed as (such as Fig.36 -(b)): .

[0348] J416: Target calculation: According to each search point arranged in J415, calculate the distance between it and the center points of m light spots of the same target light with different wavelengths and sum them up (such as Fig.36 -(c)): .

[0349] J417: Determine the accuracy according to J411. If the accuracy is met, output point M, which is the optimal point. Otherwise, adjust the search center and step size according to J418 (such as Fig.36 -(d)); J418: For point M that does not meet the conditions of J417, consider the following two situations: Case 1: If M coincides with the center point M in J415, it indicates that the initial search area is too large. In this case, the step length Δ in step J415 is updated to Δ / 2 to further narrow the range; then recalculate according to steps J416 to J417 (such as Fig.36 -(d)).

[0350] Case 2: If M does not coincide with the center point M in J415, the position of point M should be updated. In this case, point M in step J415 is updated to this point, and steps J416 to J417 are executed (such as Fig.36 -(e)).

[0351] J419: Follow steps J411 to J418 to point P λ1 ~P λm Processing is performed to merge the centers of light spots of different wavelengths of the same target light.

[0352] In the above steps, we have completed the equivalent merging of the centers of the light spots of different wavelengths of the same target light into one point (i.e., position merging). Next, we continue to merge the light spot areas of different wavelengths of the same target light (shape merging), thus completing the superposition of multiple band images. The area merging of multi-band images is not simply adding up the areas of each image and finding the average. The weight of the position distribution deviation should be considered, and the weighted average of each area should be taken. Based on this principle, in step J4, the specific merging method step J42 includes: J421: For the light spots of the same target light with different wavelengths, calculate their merged center M(x M , y M ), and then calculate the square of the distance S between the merged center M and the center of each wavelength spot i : ; J422: Based on the minimum distance deviation D calculated in J416, calculate the distance deviation weight β between the spot center of the same target light with different wavelengths and the merge center M: ; J423: According to the spot area A of the same target light with different wavelengths i , considering the image of J422 with medium-range deviation weight, calculate the weighted mean of the superposition of the spot areas of each wavelength: ; J424: Follow steps J421 to J423 to point P λ1 ~P λm The corresponding spot areas are processed to complete the merging of the spot areas of different wavelengths of the same target light.

[0353] The above has completed the recognition of target images, elimination of residual images, and merging of homologous target images, but these are only for the image of one target light. There are several target lights on a target, so it is necessary to classify the many target images processed above and classify the target light images on the same target in order to determine the spatial position of the target. Since the target lights on the same target are in the same plane, the distance from each target light to the camera is very small, so the aberration of their respective spot areas is very small; but because the scale variation of the spatial distribution of different targets is much larger than the distance from each target light to the camera, the images can be classified by area, and those with consistent areas are classified as the same target. Based on this principle, the specific target light clustering method in step R3 is as follows: R31: Assume that there are q homologous target lights after merging data, and the merging center of each homologous target image is (x Mi , y Mi ), the merged area is A Ci (i≤q), the central dark area of ​​the rearward target light is not considered in the analysis; R32: A Ci Rearrange in ascending order; R33: From A C1 To start, press A Ci With A Ci+1 Compare and calculate the relative deviation value δ i : ; R34: If δ i >δ0, then A Ci+1 With A Ci Classified as the same type of target, recorded as the rth type; Otherwise, A Ci+1 The target marker classified into the next category is the r+1 category; Where δ0 is the area resolution; R35: According to the above steps R31 to R34, suppose there are t types of targets in total. Then discard the last type of grouped targets, that is, discard the tth group, and keep the first t-1 groups as the result of target clustering (such as Fig.37 As shown in the figure, the ninth category cannot be distinguished in terms of its area change, so only targets from categories 1 to 8 are taken, and the ninth category is discarded because it cannot be distinguished as the target it belongs to).

[0354] The aforementioned area resolution δ0 is a characteristic of the light source itself and needs to be calibrated to determine its initial value. The specific calibration method is as follows: Calibrate the area resolution and determine the initial value of the area resolution: P1: Use the light targets arranged on site as calibration objects, and set all light targets to λ through the remote host 600. k Wavelength, k≤b, where b is the total number of wavelengths that each target light can emit, and all are lit.

[0355] P2: Shooting λ k An image at a wavelength, obtain the area A of each light spot in the image k,i , i≤n, n is the total number of light spots in the image.

[0356] P3: A k,i Sort in descending order to get the sequence {A k , n}, n is the total number of spots in the image, and the difference between adjacent items Δ is calculated k,j =A k , j+1 -A k , j ; j≤n, n is the total number of light spots in the image (at this time, there may be afterimages in each light spot, not all of them are complete light spots).

[0357] P4: Take δ k , 0= min(Δ k,j ) and δ k ,0>0 is taken as the area resolution of the image at this wavelength.

[0358] P5: Calculate the δ of each spot image under the type b wavelength according to P1~P4 k ,0 value.

[0359] P6: Calculate the variation value of each spot image under the wavelength of type b respectively, and select the spot with the smallest variation value as the calculation object.

[0360] P7: Take the light spot with the smallest wavelength variation value in each category as the calculation object, and calculate the deviation weight β corresponding to each wavelength of the light spot respectively. k .

[0361] P8: The δ calculated in P5 k ,0 value is calculated according to β in P7 k Perform weighted averaging to obtain the area resolution δ0: .

[0362] The advantage of this method in calculating and determining the area resolution threshold is that there is no need to set up targets separately outside the field for calibration, and calibration can be achieved directly using the targets arranged on site; because the merged area of ​​the same-source but different-wavelength target images is used for spot clustering, the resolution threshold takes into account the influence of the area differences of imaging in different bands, and the judgment accuracy is higher.

[0363] After completing the above decoding steps, the method of this embodiment further includes (refer to Fig.38 ): Integrating the decoding results of the target light image set into image tags to obtain first data specifically includes the following steps: V1: Record the timestamp and camera number when the image was taken.

[0364] V2: Determine the viewing direction of the image and the available target images for screening, using code 1 for forward direction and 0 for backward direction.

[0365] V3: Different target lights can be distinguished based on wavelength combinations.

[0366] V4: Complete the coordinates of each target light image in the image plane, and use (x i , y i )Record.

[0367] V5: Find all the target lights contained in each target and store the positions of the target lights in the same group as a set.

[0368] V6: Generate a coding sequence using the set in V5 so that each target light image has a unique identifiable number.

[0369] V6 includes: V61: If V2 is judged as 1, for each set in V5, the x coordinates of the target lights contained in it are sorted in ascending order; for example, if a target light set is {(12, 2), (5, 5), (8, 9)}, then x The coordinates are arranged in ascending order, and the sequence after ascending order is: (5, 5), (8, 9), (12, 2).

[0370] If V2 is judged as 0, for each set in V5, the x coordinates of the target lights contained in it are sorted in descending order; for example, if a target light set is {(12, 2), (5, 5), (8, 9)}, then x The coordinates are arranged in descending order, and the sequence after descending order is: (12, 2), (8, 9), (5, 5).

[0371] V62: Replace the coordinates corresponding to the target light sequence in V61 with the corresponding target light code in V3 to obtain a new sequence, which is the entire target number. For example, if the target light sequence is known to be (12, 2), (8, 9), (5, 5), and the corresponding target light codes are 001, 110, 101, then the target number is 001110101.

[0372] The above method associates and integrates the target light direction, target light image coordinates, and target number information without the help of any reference other than a single image, thus achieving autonomous identification of the target image.

[0373] Further, refer to Fig.39 As shown, to complete the target autonomous identification, the following steps are also included: N1: When the camera is triggered to collect images, each wavelength of the target light image will generate a single-channel image file in the camera and transmit it to the remote host 600 through the intra-field communication.

[0374] N2: The remote host 600 calculates and stores the image tag.

[0375] N3: Generate visual overlapped images: N4: The remote host 600 stores the camera's "Unix timestamp", "camera number" and the "viewing direction", "band number", "target image code" and "target image center" obtained in N2 as a data file DATA.

[0376] N5: Integrate the images of each band, the visualized superimposed image, and the data file DATA into one TIFF file.

[0377] Wherein, step N3 comprises: N31: Generate a blank image with the same resolution as the images of each band and the color level of each channel of each pixel is 0.

[0378] N32: Traverse each band image according to the following rules and assign a value to each pixel level of the blank image generated by N31: For any pixel (i, j) of each band image in the image plane coordinate system, if the color scale value affected by any of them is 255, the color scale of the pixel (i, j) at the corresponding position in the blank image generated by N31 is assigned a value of 255; otherwise, it is assigned a value of 0.

[0379] To facilitate understanding of the above process, an example is given below. For example, the label of an image is: (1694617868,01,100110001,100110010,100110011,491.880,514.255,906.287,675.024,1320.694,835.793,2548.923,2550.323,2806.690,2456.659,3064.456,2362.994) The annotations are as follows: Unix timestamp: 1694617868 It indicates that the image was taken at 23:11:08 on September 13, 2023.

[0380] View direction: 01 Indicates that the current viewing direction is forward.

[0381] Target image code: 100110001, 100110010, 100110011 Indicates that the image contains three targets, 233, 234, and 235, and the status of the three lights of target 233 are λ 1. λ 1+ λ 2. λ 3; The three lights of the 234 target are as follows: λ 1. λ 1+ λ 2. λ 2; The three lights of the 235 target are as follows: λ 1. λ 1+ λ 2. λ 2+ λ 3.

[0382] Target image center: 491.880,514.255 ,906.287,675.024, 1320.694,835.793 ,2548.923,2550.323, 2806.690,2456.659 ,3064.456,2362.994 Indicates 233 targets λ 1. λ 1+ λ 2. λ 3 The corresponding center coordinates of the three target light images are (491.880, 514.255), (906.287, 675.024), and (1320.694, 835.793).

[0383] The corresponding center coordinates of the three target light images of target 234 λ1, λ1+λ2, and λ2 are (2548.923, 2550.323), (2806.690, 2456.659), and (3064.456, 2362.994), respectively.

[0384] Through a TIFF file, the images of each band and the data information after joint processing are integrated. This data processing method can effectively solve the problem of a large number of images collected by each camera and the difficulty of storage and classification. In addition, since it contains all the information starting from the original image, it has strong traceability and is convenient for later verification and proofreading.

[0385] Implementation example of a spatial multi-target image autonomous identification system: A spatial multi-target image autonomous identification system, comprising: The above targets, the above imaging devices, and the above encoding devices; the number of targets arranged is a first preset number, and are arranged in a staggered manner along a preset baseline, and the target lights on all targets have the same shape and the same display direction of light; the target lights of adjacent targets on the same baseline are staggered in the shooting direction of the imaging device; the number of imaging devices arranged is a second preset number, and are used to collect images of target lights on the targets; the encoding device is used to set the on and off combination of the target lights, encode the targets, and decode the target lights images collected by the imaging device to complete autonomous identification.

[0386] Implementation example of a method for autonomously identifying multiple spatial target images: A spatial multi-target image autonomous identification method, based on the above-mentioned spatial multi-target image autonomous identification system, the method comprises: U1. Arrange target clusters: a first preset number of targets are arranged alternately along a preset baseline, and the target lights on all targets have the same shape and the same display direction of light; the target lights of adjacent targets on the same baseline are staggered in the shooting direction of the imaging device.

[0387] U2. Target coding: The on and off combination of the target lights on each target is set through the coding device to encode the target.

[0388] U3. Capture and decode target light images: Use an imaging device to capture target light images on the target to obtain a target light image set; decode the target light image set to obtain decoded data, which includes the target light direction, target light image coordinates, and the number information of the target to which the target light belongs.

[0389] U4, autonomous identification: associate the decoded data with the target light image set to complete autonomous identification.

[0390] In U1, there are more than two preset baselines, and the preset baselines are continuous space curves on any wall surface in the application scene.

[0391] Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. Any technician familiar with the art can make many possible changes and modifications to the technical solution of the present invention by using the technical content disclosed above without departing from the scope of the technical solution of the present invention, or modify it into an equivalent embodiment of equivalent changes. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention should fall within the scope of protection of the technical solution of the present invention.

Claims

1. A target for autonomous image identification, characterized in that: The target rod (100) comprises a target base (300) and a target light (200). One end of the target rod (100) is adjustably mounted on the target base (300). The target light (200) is mounted on the target rod (100) and can display light on the front and rear surfaces of the target rod (100).

2. The target for autonomous image identification according to claim 1, characterized in that: The target base (300) is provided with a base frame (303), and a group of mounting and fixing components are respectively provided at both ends of the base frame (303), and the mounting and fixing components include a fixing fastener (3031) and a pair of leveling bolts (3032). The target base (300) is provided with a mounting through hole (3033) for mounting the fixing fastener (3031), and leveling screw holes (3034) are respectively provided on both sides of the mounting through hole (3033) for mounting the pair of leveling bolts (3032).

3. The target for autonomous image identification according to claim 2, characterized in that: The bottom of the leveling bolt (3032) is spherical.

4. The target for autonomous image marking according to claim 3, characterized in that: The base frame (303) is provided with an arc guide groove (301); the target rod (100) is hinged to the target seat (300), and the hinge point is located at the center of the arc guide groove (301); a locking screw (302) is slidably provided on the arc guide groove (301); the locking screw (302) cooperates with the target rod (100) to fix the target rod (100) at a specified position.

5. The target for autonomous image marking according to any one of claims 1 to 4, characterized in that: Three target lights (200) are provided, and the three target lights (200) are evenly spaced along the target pole (100), and the lights displayed by the three target lights (200) on the front and rear surfaces are the same in the same direction and different in different directions.

6. The target for autonomous image marking according to any one of claims 1 to 4, characterized in that: The surface of the target rod (100) is provided with a low-reflectivity matte coating.

7. A target light (200) for a target for autonomous image identification as claimed in any one of claims 1 to 6, characterized in that: The invention comprises a rear scattering cover (201), a rear hyperbolic reflection cavity (202), a reflection cone (203), a lamp bead (204), a front hyperbolic reflection cavity (205), and a front scattering cover (206); the rear hyperbolic reflection cavity (202) is butt-jointed with the front hyperbolic reflection cavity (205) and the reflection cone (203) is clamped and fixed inside; a plurality of lamp beads (204) are provided and are dispersedly arranged at the front and rear sides of the reflection cone (203); the front scattering cover (206) is installed at the front end of the front hyperbolic reflection cavity (205); and the rear scattering cover (201) is installed at the rear end of the rear hyperbolic reflection cavity (202).

8. The target light (200) according to claim 7, characterized in that: A light shielding hole is provided in the centre of the front scattering cover (206) or the rear scattering cover (201); a light shielding tube (207) is provided at one end of the reflection cone (203); and the light shielding tube (207) is sleeved in the light shielding hole.

9. The target light (200) according to claim 8, characterized in that: The lamp beads (204) include LED lamp beads of multiple different wavelengths, and LED lamp beads of multiple different wavelengths are arranged on both the front and rear sides of the reflection cone (203), and the LED lamp beads of multiple different wavelengths on the same side of the reflection cone (203) are arranged in a staggered manner.

10. The target light (200) according to claim 9, characterized in that: The lamp beads (204) on the front and rear sides of the reflection cone (203) are arranged in a staggered manner.

11. The target light (200) according to claim 10, characterized in that: The optical centers of the lamp beads (204) on the front and rear sides of the reflection cone (203) are located on the same plane.

12. The target light (200) according to claim 11, characterized in that: The rear hyperbolic reflection cavity (202), the front hyperbolic reflection cavity (205) and the reflection cone (203) are coaxially arranged.

13. A method for fixing a target for image autonomous marking as claimed in any one of claims 1 to 6 on an uneven surface, characterized in that: The following steps are involved: S1: Pre-installation, passing the fixing fastener (3031) through the installation through hole (3033) on the target base (300) and driving it into the uneven surface, and making the fixing fastener (3031) not completely press the target base (300); S2: Leveling, screwing the leveling bolts (3032) into the leveling screw holes (3034) so ​​that the spherical parts at the bottom of the leveling bolts (3032) contact and abut against the uneven surface, and adjusting the screwing depth of the leveling bolts (3032) so that the posture of the target base (300) tends to the target installation posture; S3: Fixing. When the target base (300) reaches the target installation posture, tighten the fixing fastener (3031) so that the target base (300) is completely fixed, thereby completing the fixed installation of the target on the uneven surface.

14. An equal light intensity non-parallax synchronous image splitting and multi-band imaging device, characterized in that: The invention comprises a lens (400) and a frame (500), wherein the lens (400) is mounted on the frame (500), and a light splitting channel (501) and a plurality of imaging components (502) are arranged in the frame (500), wherein the light splitting channel (501) transmits light incident from the lens (400) to each imaging component (502) through multi-level light splitting and reflection to form equal-intensity light, and the imaging component (502) comprises a focusing lens (5021), an imaging sensor (5023), and a band filter (5022) for allowing a light beam of a specific wavelength to pass through.

15. The isoluminous intensity non-parallax synchronous image splitting and multi-band imaging device according to claim 14, characterized in that: The imaging component (502) is provided with four groups, and the light splitting channel (501) is provided with a primary beam splitter (5011) and two secondary beam splitters (5012). After the incident light is dispersed into two beams of light by the primary beam splitter (5011), the two beams of light are respectively dispersed into two beams of light by a secondary beam splitter (5012), thereby forming a total of four beams of light which are respectively transmitted to the four groups of imaging components (502).

16. The isoluminous intensity non-parallax synchronous image splitting and multi-band imaging device according to claim 15, characterized in that: The incident light beam is dispersed into a first beam of light (L1) and a second beam of light (L2) by a first beam splitter (5011); the first beam of light (L1) is reflected by a first reflector (M1) and then emitted to a second beam splitter (5012); dispersed into two beams of light by the second beam splitter (5012) and then respectively reflected into a corresponding imaging component (502) by a second reflector (M2) and a third reflector (M3); the second beam of light (L2) is directly emitted to another second beam splitter (5012); dispersed into two beams of light by the second beam splitter (5012), one of which is reflected into a corresponding imaging component (502) by a fourth reflector (M4) and a fifth reflector (M5) in sequence, and the other is reflected into a corresponding imaging component (502) by a sixth reflector (M6) and a seventh reflector (M7) in sequence.

17. The isoluminous intensity non-parallax synchronous image splitting and multi-band imaging device according to claim 16, characterized in that: A secondary beam splitter (5013) and a residual light absorption cavity (5014) are provided between the secondary beam splitter (5012) and the imaging component (502).

18. The isoluminous intensity non-parallax synchronous image splitting and multi-band imaging device according to claim 17, characterized in that: The primary beam splitter (5011), the secondary beam splitter (5012) and the secondary beam splitter (5013) are arranged in parallel.

19. The isoluminous intensity non-parallax synchronous image splitting and multi-band imaging device according to claim 18, characterized in that: The first reflector (M1), the fourth reflector (M4) and the sixth reflector (M6) are arranged in parallel; the second reflector (M2), the third reflector (M3), the fifth reflector (M5) and the seventh reflector (M7) are arranged in parallel.

20. The isoluminous intensity non-parallax synchronous image splitting and multi-band imaging device according to any one of claims 14 to 19, characterized in that: A heat-insulating cavity (503) is provided inside the outer shell surface of the frame (500).

21. The isoluminous intensity non-parallax synchronous image splitting and multi-band imaging device according to claim 20, characterized in that: A heat-insulating cavity (503) is provided in the middle of the frame (500).

22. A coding device for target coding, characterized in that: It comprises a remote host (600), one or more handheld terminals (601) and one or more target encoding modules (602); The handheld terminal (601) is used to communicate with the remote host (600) to synchronize the database, and is also used to communicate with the target coding module (602) to add, delete, check and modify the target coding information; The target encoding module (602) is integrated in the target and is used to synchronize the real-time encoding information of the target to the remote host (600); it is also used to communicate with the handheld terminal (601) to receive addition, deletion, query and modification instructions from the handheld terminal (601); and it is also used to send the target's encoding and status information to the handheld terminal (601).

23. The encoding device for target encoding according to claim 22, characterized in that: The handheld terminal (601) comprises a first radio frequency unit (6011), a first storage unit (6012), a first calculation unit (6013) and a WIFI unit (6014); The first radio frequency unit (6011) comprises an RFID tag, and is used to communicate with the target encoding module (602); The first storage unit (6012) is used to store data of the handheld terminal (601); The first calculation unit (6013) is used for calculating the coding information of the handheld terminal (601); The WIFI unit (6014) is used to communicate with the remote host (600).

24. The encoding device for target encoding according to claim 23, characterized in that: The target encoding module (602) comprises a second radio frequency unit (6021), a second storage unit (6022), a second calculation unit (6023) and a NET unit (6024); The second radio frequency unit (6021) comprises an RFID tag, and is used for communicating with the handheld terminal (601); The second storage unit (6022) is used to store data of the target encoding module (602); The second calculation unit (6023) is used for calculating the coding information of the target coding module (602); The NET unit (6024) is used to communicate with the remote host (600).

25. The encoding device for target encoding according to claim 24, characterized in that: The handheld terminal (601) communicates with the target encoding module (602) via a first radio frequency unit (6011) and a second radio frequency unit (6021).

26. The encoding device for target encoding according to any one of claims 22 to 25, characterized in that: The network relationship between the remote host (600) and the one or more target encoding modules (602) includes: The remote host (600) is capable of performing unidirectional reading and writing of data on the one or more target encoding modules (602).

27. The encoding device for target encoding according to claim 26, characterized in that: The network relationship between the remote host (600) and the one or more handheld terminals (601) includes: The remote host (600) is capable of reading and writing data to the one or more handheld terminals (601); The one or more handheld terminals (601) are capable of reading data from the remote host (600).

28. The encoding device for target encoding according to claim 27, characterized in that: The remote host (600) is capable of publishing information to off-site via a mobile network, wherein the mobile network includes a network provided by a communication service provider.

29. The encoding device for target encoding according to claim 28, characterized in that: The network relationship between the handheld terminal (601) and the target encoding module (602) includes: The handheld terminal (601) is capable of reading data from the target encoding module (602).

30. The encoding device for target encoding according to claim 29, characterized in that: Before the handheld terminal (601) reads data from the target encoding module (602), the handheld terminal (601) needs to communicate with the remote host (600) to synchronize the database.

31. A target coding control method, based on the coding device for target coding according to any one of claims 22 to 30, characterized in that: include: T1, communicating with the remote host (600) through the handheld terminal (601) to synchronize the database, communicating with the target coding module (602) and adding, deleting, checking and modifying the target coding information; T2. Communicate with the handheld terminal (601) via the target encoding module (602) to receive addition, deletion, query and modification instructions from the handheld terminal (601); send the target encoding and status information to the handheld terminal (601) via the target encoding module (602).

32. The target coding control method according to claim 31, characterized in that: The T1 includes: A1: For a target whose code is to be initialized or modified, a handheld terminal (601) is used to synchronize the code library with a remote host (600) via a WIFI unit (6014) and update the code library in the first storage unit (6012); A2: inputting the proposed target number through the handheld terminal (601), and encoding it through the first calculation unit (6013); A3: The first calculation unit (6013) reads the data in the first storage unit (6012) and compares the input, encoded target number with the data. If the target number is repeated with the existing code, the calculation unit returns to re-enter the target number. If the target number is not repeated, the input, encoded target number is written into the first storage unit (6012). A4: triggering the RFID tag of the first radio frequency unit (6011) to transmit to the RFID tag of the target second radio frequency unit (6021); A5: When the RFID tag of the second radio frequency unit (6021) receives the code writing instruction, it triggers the second calculation unit (6023) to read and write instructions, and the second storage unit (6022) receives and writes the new code; A6: The new code written in the second storage unit (6022) is synchronized to the remote host (600) through the NET unit (6024), and its code library is updated; A7: The second calculation unit (6023) outputs the new code of the second storage unit (6022) to the corresponding lamp bead (204) of each target lamp (200), and controls the on and off combination of the lamp bead (204).

33. The target coding control method according to claim 32, characterized in that: The T2 includes: B1: When the handheld terminal (601) reaches the sensing range of the RFID tag of the second radio frequency unit (6021) of the target, the RFID tag of the first radio frequency unit (6011) on the handheld terminal (601) communicates and activates with the RFID tag of the second radio frequency unit (6021) on the target; B2: When the RFID tag of the second radio frequency unit (6021) on the target receives a query instruction, the read and write function of the second calculation unit (6023) is triggered to read the latest target coding information and working status information in the second storage unit (6022); B3: The RFID tag of the second radio frequency unit (6021) on the target feeds back the latest target coding information and working status information to the RFID tag of the first radio frequency unit (6011) on the handheld terminal (601), which is then decoded by the first calculation unit (6013) and displayed on the handheld terminal (601).

34. The target coding control method according to claim 33, characterized in that: Also includes: The coding information of the target is read, written, collected and modified by the remote host (600), and the on / off combination of the target light (200) is adjusted.

35. The target coding control method according to claim 34, characterized in that: The reading, writing, collecting and modifying of the target's coded information by the remote host (600) includes: C1: The remote host (600) sends a coded information collection instruction to each target; C2: triggering the second computing unit (6023) of each target to execute the coding information read and write instruction, and sending the coding information stored in the second storage unit (6022) to the remote host (600) through the NET unit (6024); C3: The remote host (600) checks the collected target coding information, and if there is a duplicate code, changes the duplicate code, issues a code change instruction to the corresponding target, and sends the modified coding information to the corresponding target; C4: The second computing unit (6023) of the corresponding target receives the code change instruction sent by the remote host (600) and receives the code information after the code change, and writes the code information after the code change into the second storage unit (6022) for refreshing; C5: The second calculation unit (6023) controls the corresponding lamp beads (204) of the target lamp (200) according to the modified coded information, and adjusts the on and off combination thereof.

36. The target coding control method according to claim 35, characterized in that: Also includes: Status monitoring: when a target light (200) fails, the target is monitored for status through the encoding device; Power failure recovery: when the system is powered off and then restored, and the target light (200) is restored to a default state, the target light (200) is restarted through the encoding device to restore the preset state of the target.

37. The target coding control method according to claim 36, characterized in that: The condition monitoring includes: D1: Using optical simulation, the most unfavorable illumination distribution for different numbers of damaged lamp beads (204) is calculated, and the allowable number of damaged lamp beads (204) is determined by comprehensively considering illumination uniformity and the minimum illumination resolution of the camera; D2, collecting the on and off status of each lamp bead (204) at a preset frequency through the second calculation unit (6023), and generating a corresponding monitoring code; for the lamp bead (204) of a certain wavelength in the same target lamp (200), when the number of damaged lamp beads (204) collected is the number allowed in D1, the lamp bead (204) is still recorded as all lit, otherwise it is recorded as all extinguished; when the lamp bead (204) is marked as all extinguished, the corresponding monitoring code is written into the second storage unit (6022); D3, comparing the monitoring code generated in D2 with the original code in the second storage unit (6022), if the comparison results are consistent, it is determined that the wavelength lamp bead (204) is normal and the current state is maintained; if the comparison results are inconsistent, it is determined that the wavelength lamp bead (204) is damaged, the second calculation unit (6023) sends a lighting termination instruction, and all the target lamps (200) of the target are turned off; D4: For the case determined as damaged in D3, the second storage unit (6022) sends the stored monitoring code to the remote host (600) via the NET unit (6024) and issues an alarm for maintenance; D5: The remote host (600) publishes maintenance information to the off-site terminal via the mobile network.

38. The target coding control method according to claim 37, characterized in that: The power failure recovery includes: E1: The second storage unit (6022) has stored the target coding information before power failure; E2: The second computing unit (6023) detects power-on information and performs a self-check of the target light (200) according to D1 to D5; E3: For a target light (200) that has self-checked normally, the second calculation unit (6023) outputs the target code in the second storage unit (6022) to the corresponding lamp bead (204) of the target light (200), and restores the on and off combination of the lamp bead (204).

39. A target coding method, based on the target according to any one of claims 1 to 6 and the target light according to any one of claims 7 to 12, characterized in that: include: set up There are a target lamps (200) on a single target, each target lamp (200) has lamp beads (204) of b wavelengths, and excluding the target where the target lamp (200) is completely extinguished, each target lamp (200) has a total of 2 b -1 combinations; and each target has a target lights (200), so for a target with a target lights (200) and each target light (200) has b wavelengths, the number of target numbers that can be expressed is: (2 b -1) a , the encoding method is: F1: Number of coding bits for a single target: Each target light (200) has lamp beads (204) of b wavelengths, and each wavelength of the lamp bead (204) needs to occupy 1 bit of coding to indicate two states of on or off, where 1 indicates on and 0 indicates off. Therefore, each target light (200) requires b bits of coding, and a target light (200) of a single target requires a·b bits of coding; F2: Single target light coding: For any target light i on the target, the on / off status codes of b wavelengths are sequentially connected into a target light coding to represent the identity of the current target light (200), and each target light coding has b bits; F3: Single target code: Connect the single target light codes of the first target light (200) to the bth target light (200) in order from left to right to obtain the code of the entire target; F4: Convert target number and target code.

40. The target encoding method according to claim 39, characterized in that: The F4 includes: Convert target number to target code: G1: Assume that the user inputs the decimal number of the target to be encoded through the handheld terminal (601) or the remote host (600) as k 10 , compare A1 to A7 with the existing codes. If they are the same as the existing codes, return to prompt for re-entry, otherwise enter G2; G2: Assume that each target has a target lights (200), each target light (200) has b wavelengths, and the decimal number K is calculated by the first calculation unit (6013) or the remote host (600). 10 Convert to 2 b Base code K 2b , where number K 10 The initial value of is: ； G3: Check K through the first computing unit (6013) or the remote host (600) 2b Does it contain 0? If it does, then K 10 After adding 1, return to G2 to recalculate; if it does not contain 0, enter G4; G4: Calculate K 10 -K0+1, and the decimal number k entered by the user 10 Compare, if K 10 -K0+1=k 10 , then K 10 Convert to binary code K2 and write into the second storage unit (6022) according to the method from A1 to A7; if K 10 -K0+1≠k 10 , then K 10 After adding 1, return to G2 and recalculate.

41. The target encoding method according to claim 40, characterized in that: The F4 also includes: Convert target codes to target numbers: H1: According to B1 to B3, the binary code K2 is read from the second storage unit (6022) by the handheld terminal (601) or the remote host (600); H2: Convert the binary code K2 into 2 through the first computing unit (6013) or the remote host (600) b Base code K 2-2b ; H3: The first computing unit (6013) or the remote host (600) converts the decimal code K 10 Convert to 2 b Base code K 2b , where K 10 The initial value K0 is calculated in the same way as G2; H4: K is calculated by the first computing unit (6013) or the remote host (600) 2-2b With K 2b For comparison, if K 2b =K 2-2b , then K 10 -K0+1 output is the decimal number of binary code K2; if K 2b ≠K 2-2b , then K 10 After adding 1, return to H3 and recalculate.

42. A method for decoding a target light image, which is based on the equal-intensity parallax-free synchronous image splitting and multi-band imaging device as described in any one of claims 14 to 21 to obtain a target light image set of a target cluster consisting of the target described in any one of claims 1 to 6 and the target light described in any one of claims 7 to 12, and decodes the target light image set, characterized in that: The following steps are involved: R1. Identify the target light spots and target light directions on the images of each wavelength in the target light image set, and remove the target light spots that do not meet the preset requirements; R2, screening the light spots of each wavelength image, merging the light spots from the same target light (200) in each wavelength image to obtain a target light image, and solving the coordinates and area of ​​the center of the target light image; R3. Classify the target lights (200) according to the area of ​​the target light images, and classify the target lights (200) with the same area as the same target.

43. The method for decoding a target light image according to claim 42, characterized in that: The R1 comprises: I1: Binarize the forward and backward target light images respectively, obtain the outer boundary through Canny edge detection, and get the spot area; restore the center coordinates of the target light; I2: Calculate the variability E of the light spot in the image R , according to the E R Determine the viewing direction; I3: For each image, select a light spot with the smallest variation to determine the viewing direction.

44. The method for decoding a target light image according to claim 43, characterized in that: The I1 includes: Binarization processing is performed on the forward and backward target light images respectively; The identified boundary pixel center is stored as the boundary point (x Bi , j , y Bi , j ), (x Bi , j , y Bi , j ) represents the coordinates of the jth boundary point of the ith light spot; the total pixel area A inside the boundary is calculated i ; The coordinates of the center point G (x Gi , j , y Gi , j ), (x Gi , j , y Gi , j ) represents the center of the ith spot. The central dark area is not considered when calculating the backward target light. Gi , j , y Gi , j ): 。 45. The method for decoding a target light image according to claim 44, characterized in that: The I2 includes: I21: Calculate the centroid G of the i-th light spot i The distance S to the jth boundary point i , j : ； I22: Calculate the equivalent circle radius R of the i-th spot ei : ； I23: For the i-th light spot, the equivalent circle radius R ei As a reference, calculate S i , j With the equivalent circle radius R ei The deviation, E Ri That is the variability of the light spot: ； E Ri The smaller the value, the lower the degree of contour change caused by occlusion. When the light spot is a standard circle, the value should be 0.

46. ​​The method for decoding a target light image according to claim 45, characterized in that: The I3 includes: I31: Taking the center of the target light spot as the starting point and the outer boundary of the detection as the limit, obtain the distribution of the gray value k of the image along the x and y directions respectively, and calculate the corresponding gray sample variance S respectively x and S y : ； ； I32: Construct the targeted discriminant: ； I33: If Δ=0, it is determined that the target light (200) in the image is facing forward; if Δ≠0, it is determined that the target light (200) in the image is facing backward.

47. The method for decoding a target light image according to claim 46, characterized in that: The R1 further comprises: According to the variation E R Combined spot area A i The integrity of the light spot is evaluated, and the light spots that meet the following conditions should be eliminated: ； in is the variation threshold of the unobstructed light spot.

48. The method for decoding a target light image according to claim 47, characterized in that: Also includes: Calibrate the variability threshold and determine the initial value of the variability threshold: Q1: Use the light targets arranged on site as calibration objects and set all light targets to λ through the remote host (600). k wavelength, k≤b, where b is the total number of wavelengths that can be emitted by each target light (200), and all are lit; Q2: Shooting λ k 1 image at wavelength, obtain the area A of each light spot in the image k,i , spot variability E Rk,i ; i≤n, n is the total number of light spots in the image; Q3: Keep E Rk,i With A k,i The corresponding relationship between A k,i Arrange into a sequence k , n }, and obtain the corresponding spot variability sequence {E Rk,n }; Q4: Find the sequence {E Rk,n }The minimum value of E Rk,m , sequence {A k , n The corresponding item is A k , m ; Q5: Find the sequence {E Rk,n }The maximum value of E Rk,p , sequence {A k , n The corresponding item is A k , p ; Q6: If A in Q5 k , p In the sequence {A k , n } is the smallest, then calculate λ as follows k The area under the wavelength is A k,i The spot variation threshold E R0(k，i) : ； Q7: If A in Q5 k , p In the sequence {A k , n } is not the smallest, remove the item and re-execute Q5.

49. The method for decoding a target light image according to claim 48, characterized in that: The R2 comprises: J1: Obtain the outer boundary and center coordinates of the target light image of each wavelength, and count the number of light spots in the image of each wavelength respectively. The central dark area of ​​the backward target light is not considered during the analysis; J2: For a target light (200) with b wavelengths, the wavelength image with the largest number of light spots is taken as the reference, and its wavelength is λ t , calculate the distance between the center of each spot image of this wavelength and the center of the spot of other wavelength images: ； Among them, x k The horizontal coordinate of the center of the kth spot in the wavelength image with the largest number of spots; y k Indicates the ordinate of the center of the kth spot in the wavelength image with the largest number of spots; x λc,n Indicates wavelength as λ c The horizontal coordinate of the center of the nth spot in the wavelength image; y λc,n Indicates wavelength as λ c The vertical coordinate of the center of the nth spot in the wavelength image; D(k, λ c , n) represents the kth spot in the wavelength image with the largest number of spots and the wavelength λ c The center distance of the nth spot in the wavelength image; J3: At wavelength λ c Among the many points, when a certain point can make the above-calculated D(k, λ c , n) value is the smallest, then the point has the largest number of spots and the wavelength is λ t The k-th point distance is used to achieve overlap; using D(k, λ c , n), the wavelength is established as λ according to the following formula t The corresponding relationship between each target point and other wavelength targets: ； Among them, P(λ t , k) indicates the largest number of light spots and a wavelength of λ t The kth point of c , q) represents the wavelength λ c The qth point of P(λ t , k) overlap; J4: Merge the light spot centers of the light spots determined to be the same target light (200).

50. The method for decoding a target light image according to claim 49, characterized in that: The J4 includes: J41. Equivalently merge the light spot centers of different wavelengths of the same target light (200); J42. Merge the spot areas of the same target light (200) with different wavelengths.

51. The method for decoding a target light image according to claim 50, characterized in that: The J41 includes: J411: Set the resolution accuracy: When calculating according to J412~J418, when the search center gradually approaches the search center M, the step size will tend to 0; considering the discreteness of digital imaging, Δ≤δ is used as the cutoff condition, where Δ is the step size and δ is the pixel size of the imaging sensor; J412: Determine the initial search area: Based on the center point P of the light spot with different wavelengths of the same target light (200) λ1 ~P λm The coordinates determine the initial search range, where 1≤m≤b, and min(x i )≤x≤max(x i ), min(y i )≤y≤max(y i ) area as the initial area, where 1≤i≤m; J413: Determine the initial search center: J412 determines the geometric center G formed by all points in the area as the initial search center point M, the coordinates are: ； J414: Determine the initial search step length: half of the minimum value of the height and width direction of the area determined by J412 is used as the initial search step length Δ: ； J415: Search area: With the optimal point M as the center and Δ as the step length, search points are arranged in 8 orthogonal directions around it. For the first calculation, point M is point G; the coordinates of each search point are expressed as: ； J416: Target calculation: According to each search point arranged in J415, calculate the distance between it and the center points of m light spots of the same target light (200) with different wavelengths and sum them: ； J417: Determine the accuracy according to J411. If the accuracy is met, output point M, which is the optimal point. Otherwise, adjust the search center and step size according to J418. J418: For point M that does not meet the conditions of J417, consider the following two situations: Case 1: If M coincides with the center point M in J415, it indicates that the initial search area is too large. In this case, the step size Δ in J415 is updated to Δ / 2 to further narrow the range; then recalculate according to J416~J417; Case 2: If M does not coincide with the center point M in J415, the position of point M should be updated. In this case, point M in J415 is updated to this point, and then J416 to J417 are executed; J419: Press J411~J418 to point P λ1 ~P λm Processing is performed to complete the merging of the centers of light spots with different wavelengths of the same target light (200).

52. The method for decoding a target light image according to claim 51, characterized in that: The J42 includes: J421: For the light spots of different wavelengths of the same target light (200), calculate their merged center M (x M , y M ), and then calculate the square of the distance S between the merged center M and the center of each wavelength spot i : ； J422: Based on the minimum distance deviation D calculated in J416, calculate the distance deviation weight β between the spot center of the same target light (200) with different wavelengths and the merged center M: ； J423: According to the spot area A of the same target light (200) with different wavelengths i , considering the image of J422 with medium-range deviation weight, calculate the weighted mean of the superposition of the spot areas of each wavelength: ； J424: Press J421~J423 to point P λ1 ~P λm The corresponding light spot areas are processed to complete the merging of light spot areas of different wavelengths of the same target light (200).

53. The method for decoding a target light image according to claim 52, characterized in that: The R3 further comprises: R31: Assume that there are q homologous target lights after merging data, and the merging center of each homologous target image is (x Mi , y Mi ), the merged area is A Ci , i≤q, the central dark area of ​​the rearward target light is not considered in the analysis; R32: A Ci Rearrange in ascending order; R33: From A C1 To start, press A Ci With A Ci+1 Compare and calculate the relative deviation value δ i : ； R34: If δ i >δ0, then A Ci+1 With A Ci Classified as the same type of target, recorded as the rth type; Otherwise, A Ci+1 The target marker classified into the next category is the r+1 category; Where δ0 is the area resolution; R35: According to R31 to R34 above, if there are t types of targets in total, then discard the last type of grouped targets, that is, discard the tth group, and retain the first t-1 groups as the result of target clustering grouping.

54. The method for decoding a target light image according to claim 53, characterized in that: Also includes: Calibrate the area resolution and determine the initial value of the area resolution: P1: Use the light targets arranged on site as calibration objects and set all light targets to λ through the remote host (600). k wavelength, k≤b, where b is the total number of wavelengths that can be emitted by each target light (200), and all are lit; P2: Shooting λ k An image at a wavelength, obtain the area A of each light spot in the image k,i , i≤n, n is the total number of light spots in the image; P3: A k,i Sort in descending order to get the sequence {A k , n }, n is the total number of spots in the image, and the difference between adjacent items Δ is calculated k,j =A k , j+1 -A k , j ; j≤n, n is the total number of light spots in the image; P4: Take δ k , 0= min(Δ k,j ) and δ k ,0>0 is taken as the area resolution of the image at this wavelength; P5: Calculate the δ of each spot image under the type b wavelength according to P1~P4 k ,0 value; P6: Calculate the variation value of each spot image under the wavelength of type b respectively, and select the spot with the smallest variation value as the calculation object; P7: Take the light spot with the smallest wavelength variation value in each category as the calculation object, and calculate the deviation weight β corresponding to each wavelength of the light spot respectively. k ; P8: The δ calculated in P5 k ,0 value is calculated according to β in P7 k Perform weighted averaging to obtain the area resolution δ0: 。 55. The method for decoding a target light image according to any one of claims 42 to 54, characterized in that: Also includes: The decoding results of the target light image set are integrated into image tags to obtain first data.

56. The method for decoding a target light image according to claim 55, characterized in that: Integrate the decoding results of the target light image set into image tags including: V1: Record the timestamp and camera number when the image was taken; V2: Determine the viewing direction of the image and the available target image screening, with code 1 for forward direction and 0 for backward direction; V3: Differentiate between different target lights (200) according to the wavelength combination; V4: Complete the coordinates of each target light image in the image plane, and use (x i , y i )Record; V5: Find all the target lights (200) contained in each target, and store the positions of the target lights in the same group as a set; V6: Generate a coding sequence using the set in V5 so that each target light image has a unique identifiable number.

57. The method for decoding a target light image according to claim 56, characterized in that: The V6 includes: V61: If V2 is judged as 1, for each set in V5, the x-coordinates of the target lights contained therein are sorted in ascending order; If V2 is judged as 0, for each set in V5, the x coordinates of the target lights contained therein are sorted in descending order; V62: Replace the coordinates corresponding to the target light sequence in V61 with the corresponding target light code in V3 to obtain a new sequence, which is the entire target number.

58. The method for decoding a target light image according to claim 57, characterized in that: It also includes completing the target autonomous identification, the steps are as follows: N1: When the camera is triggered to collect images, each wavelength of the target light image will generate a single-channel image file in the camera and transmit it to the remote host (600) through intra-field communication; N2: The remote host (600) calculates and stores the image tag; N3: Generate visual overlapped images: N4: The remote host (600) stores the camera's "Unix timestamp", "camera number" and the "viewing direction", "band number", "target image code" and "target image center" obtained in N2 into a data file DATA; N5: Integrate the images of each band, the visualized superimposed image, and the data file DATA into one TIFF file.

59. The method for decoding a target light image according to claim 58, characterized in that: The N3 includes: N31: Generate a blank image with the same resolution as the images of each band and the color level of each channel of each pixel is 0; N32: Traverse each band image according to the following rules and assign a value to each pixel level of the blank image generated by N31: For any pixel (i, j) of each band image in the image plane coordinate system, if the color scale value affected by any of them is 255, the color scale of the pixel (i, j) at the corresponding position in the blank image generated by N31 is assigned a value of 255; otherwise, it is assigned a value of 0.

60. A spatial multi-target image autonomous identification system, characterized in that: include: The target according to any one of claims 1 to 6; The imaging device according to any one of claims 14 to 21; The encoding device as claimed in any one of claims 22 to 30; The number of targets arranged is a first preset number, and they are arranged in a staggered manner along a preset baseline, and the target lights (200) on all targets have the same shape and display the same direction of light; the target lights (200) on adjacent targets on the same baseline are staggered in the shooting direction of the imaging device; The number of the imaging devices arranged is a second preset number, and is used to collect the target light image on the target; The encoding device is used to set the on / off combination of the target light (200), encode the target, and decode the target light image captured by the imaging device to complete autonomous identification.

61. A spatial multi-target image autonomous identification method, based on the spatial multi-target image autonomous identification system of claim 60, characterized in that: The method comprises: U1. Arranging a target cluster: arranging a first preset number of targets in a staggered manner along a preset baseline, wherein target lights (200) of the same shape on all targets have the same display direction of light; and target lights (200) of adjacent targets on the same baseline are staggered in the shooting direction of the imaging device; U2, target coding: the coding device is used to set the on and off combination of the target lights (200) on each target, thereby coding the target; U3, collecting and decoding target light images: using the imaging device to collect the target light images on the target to obtain a target light image set; decoding the target light image set to obtain decoded data, the decoded data including the target light direction, the target light image coordinates, and the number information of the target to which the target light belongs; U4, autonomous identification: associate the decoded data with the target light image set to complete autonomous identification.

62. The spatial multi-target image autonomous identification method according to claim 61 is characterized in that: In the U1, there are more than two preset baselines, and the preset baselines are continuous space curves on any wall surface in the application scene.

Images